-
Notifications
You must be signed in to change notification settings - Fork 1
Expand file tree
/
Copy pathindex.html
More file actions
1768 lines (1672 loc) · 69.8 KB
/
index.html
File metadata and controls
1768 lines (1672 loc) · 69.8 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
<!DOCTYPE html>
<html>
<head>
<title>VLEO-Bench</title>
<style>
.hidden {
display: none;
}
</style>
<script src="https://cdn.jsdelivr.net/npm/chart.js"></script>
<script src="https://kit.fontawesome.com/f8ddf9854a.js" crossorigin="anonymous"></script>
<meta charset="utf-8">
<meta name="description"
content="A Comprehensive Benchmark of Vision-Language Models for Earth Observation (EO) Data">
<meta name="keywords" content="VLEO-Bench, VLM, VLM Evaluation, Vision Language Model, Large Language Model, Large Multimodal Model, artificial intelligence, AI, AGI, artificial general intelligence, Remote Sensing, Earth Observation">
<meta name="viewport" content="width=device-width, initial-scale=1">
<title> VLEO-Bench: A Comprehensive Benchmark of Vision-Language Models for Earth Observation (EO) Data</title>
<link rel="icon" href="./static/images/vleo-icon.png">
<link href="https://fonts.googleapis.com/css?family=Google+Sans|Noto+Sans|Castoro" rel="stylesheet">
<link rel="stylesheet" href="./static/css/bulma.min.css">
<link rel="stylesheet" href="./static/css/bulma-carousel.min.css">
<link rel="stylesheet" href="./static/css/bulma-slider.min.css">
<link rel="stylesheet" href="./static/css/fontawesome.all.min.css">
<link rel="stylesheet" href="https://cdn.jsdelivr.net/gh/jpswalsh/academicons@1/css/academicons.min.css">
<link rel="stylesheet" href="./static/css/index.css">
<link rel="stylesheet" href="./static/css/leaderboard.css">
<!-- <link href="https://unpkg.com/tabulator-tables@5.5.2/dist/css/tabulator_bulma.min.css" rel="stylesheet">
<script type="text/javascript" src="https://unpkg.com/tabulator-tables@5.5.2/dist/js/tabulator.min.js"></script> -->
<script type="text/javascript" src="static/js/sort-table.js" defer></script>
<script src="https://ajax.googleapis.com/ajax/libs/jquery/3.5.1/jquery.min.js"></script>
<script defer src="./static/js/fontawesome.all.min.js"></script>
<script src="./static/js/bulma-carousel.min.js"></script>
<script src="./static/js/bulma-slider.min.js"></script>
<script src="./static/js/index.js"></script>
<script src="./static/js/question_card.js"></script>
<script src="./data/results/data_setting.js" defer></script>
<script src="./data/results/model_scores.js" defer></script>
<script src="./visualizer/data/data_public.js" defer></script>
</head>
<body>
<nav class="navbar" role="navigation" aria-label="main navigation">
<div class="navbar-brand">
<a role="button" class="navbar-burger" aria-label="menu" aria-expanded="false">
<span aria-hidden="true"></span>
<span aria-hidden="true"></span>
<span aria-hidden="true"></span>
</a>
</div>
<div class="navbar-menu">
<div class="navbar-start" style="flex-grow: 1; justify-content: center;">
<div class="navbar-item has-dropdown is-hoverable">
<a class="navbar-link">
More Research
</a>
<div class="navbar-dropdown">
</a>
</div>
</div>
</div>
</div>
</nav>
<section class="hero">
<div class="hero-body">
<div class="container is-max-desktop">
<div class="columns is-centered">
<div class="column has-text-centered">
<h1 class="title is-1 publication-title is-bold">
<img src="static/images/vleo-icon.png" style="width:1em;vertical-align: middle" alt="Logo"/>
<span class="VLEO-Bench" style="vertical-align: middle">VLEO-Bench</span>
</h1>
<h2 class="subtitle is-3 publication-subtitle">
A Comprehensive Benchmark of Vision-Language Models for Earth Observation (EO) Data
</h2>
<div class="is-size-5 publication-authors">
<span class="author-block">
<a href="https://danielz.ch/" style="text-decoration: none; color: inherit;">Chenhui Zhang<sup style="color:#6fbf73;">†,1</sup></a>,
</span>
<span class="author-block">
<a href="https://sherriewang.github.io/" style="text-decoration: none; color: inherit;">Sherrie Wang<sup style="color:#6fbf73;">1</sup></a>
,
</span>
</div>
<br>
<div class="is-size-5 publication-authors">
<span class="author-block"><sup style="color:#6fbf73;">1</sup>Institute for Data, Systems, and Society, Massachusetts Institute of Technology</span>
</div>
<br>
<div class="is-size-5 publication-authors">
<span class="author-block">†Corresponding to:</span>
<span class="author-block"><a href="chenhui5@mit.edu">chenhui5@mit.edu</a></span>
</div>
<div class="column has-text-centered">
<div class="publication-links">
<!-- PDF Link. -->
<span class="link-block">
<!-- @PAN TODO: change links -->
<a href="https://arxiv.org/abs/2401.17600"
class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<i class="fas fa-file-pdf"></i>
</span>
<span>arXiv</span>
</a>
</span>
<span class="link-block">
<a href="https://huggingface.co/papers/2401.17600"
class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<p style="font-size:18px">🤗</p>
</span>
<span>HF Paper</span>
</a>
</span>
<span class="link-block">
<a href="https://huggingface.co/collections/mit-ei/vleo-benchmark-datasets-65b789b0466555489cce0d70"
class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<!-- <i class="far fa-images"></i> -->
<p style="font-size:18px">🤗</p>
<!-- 🔗 -->
</span>
<span>Dataset</span>
</a>
</span>
<span class="link-block">
<a href="https://github.com/Earth-Intelligence-Lab/vleo-bench"
class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<i class="fab fa-github"></i>
</span>
<span>Code</span>
</a>
</span>
<!-- Dataset Link. -->
<!-- Leaderboard Link. -->
<span class="link-block">
<a href="#leaderboard"
class="external-link button is-normal is-rounded is-dark">
<span class="icon has-text-white">
<i class="fa-solid fa-trophy"></i>
<!-- <p style="font-size:18px">🏆</p> -->
</span>
<span>Leaderboard</span>
</a>
</span>
<!-- Visualization Link. -->
<!-- Twitter Link. -->
<!-- <span class="link-block">
<a href="https://twitter.com/danielz233/status/xxx"
class="external-link button is-normal is-rounded is-dark">
<span class="icon has-text-white">
<i class="fa-brands fa-x-twitter"></i>
</span>
<span>Twitter</span>
</a>
</span>
<span class="link-block">
<a href="#examples"
class="external-link button is-normal is-rounded is-dark">
<span class="icon has-text-white">
<i class="fa-solid fa-book"></i>
</span>
<span>Examples</span>
</a>
</span> -->
</div>
</div>
</div>
</div>
</div>
</div>
</section>
<style>
.center {
display: block;
margin-left: auto;
margin-right: auto;
width: 80%;
}
</style>
<section class="hero teaser">
<div class="container is-max-desktop">
<!-- <div class="hero-body">
<img src="static/images/tease_scores.png" alt="Examples from the dataset"/>
<h2 class="subtitle has-text-centered">
<span class="dnerf">Nerfies</span> turns selfie videos from your phone into
free-viewpoint
portraits.
</h2>
</div> -->
<!-- <div class="box m-5"> -->
<div class="content has-text-centered">
<img src="static/images/teaser_horizontal.svg" alt="Overview of VLEO-Bench"/>
<p> Overview of the VLEO-Bench dataset. VLEO-Bench presents 11 challenging scenarios motivated by real-world applications of Earth Observation (EO) data. We aim to test the scene understanding, localization, counting, and change detection abilities of state-of-the-art instruction-following VLMs. </p>
</div>
<!-- </div> -->
</div>
</div>
</section>
<section class="section">
<div class="container" style="margin-bottom: 2vh;">
<!-- Abstract. -->
<div class="columns is-centered has-text-centered">
<div class="column is-four-fifths">
<h2 class="title is-3">🔔News</h2>
<div class="content has-text-justified">
<p>
<b>🔥[2024-01-22]: Initial release of our benchmark!</b>
</p>
</div>
<h2 class="title is-3">Introduction</h2>
<div class="content has-text-justified">
<p>
Large Vision-Language Models (VLMs) have demonstrated impressive performance on complex tasks involving visual input with natural language instructions. However, it remains unclear to what extent capabilities on natural images transfer to Earth observation (EO) data, which are predominantly satellite and aerial images less common in VLM training data. In this work, we propose a comprehensive benchmark to gauge the progress of VLMs toward being useful tools for EO data by assessing their abilities on scene understanding, localization and counting, and change detection tasks. Motivated by real-world applications, our benchmark includes scenarios like urban monitoring, disaster relief, land use, and conservation. We discover that, although state-of-the-art VLMs like GPT-4V possess extensive world knowledge that leads to strong performance on open-ended tasks like location understanding and image captioning, their poor spatial reasoning limits usefulness on object localization and counting tasks.
</p>
</div>
</div>
</div>
<!--/ Abstract. -->
</div>
</section>
<!-- DATASET SECTION -->
<section class="hero is-light is-small">
<div class="hero-body has-text-centered">
<h1 class="title is-1 VLEO-Bench">
<img src="static/images/vleo-icon.png" style="width:1em;vertical-align: middle" alt="Logo"/>
<span class="VLEO-Bench" style="vertical-align: middle">VLEO-Bench</span>
</h1>
</div>
</section>
<!-- <section class="section">
<div class="container" style="margin-bottom: 2vh;">
<div class="columns is-centered has-text-centered">
<div class="column is-four-fifths">
<h2 class="title is-3">Introduction</h2>
<div class="content has-text-justified">
<p> -->
<section class="section">
<div class="container">
<div class="columns is-centered has-text-centered">
<!-- <div class="column is-full-width has-text-centered"> -->
<div class="column is-four-fifths">
<h2 class="title is-3">Overview</h2>
<div class="content has-text-justified">
<p>
In this paper, we provide an application-focused evaluation of instruction-following VLMs like GPT-4V for different capabilities in EO, including location understanding, zero-shot remote sensing scene understanding, world knowledge, text-grounded object localization and counting, and change detection. These capabilities provide the EO community with pathways for impact in real-world application areas, including urban monitoring, disaster relief, land use, and conservation.
</p>
<img src="static/images/teaser_vertical.svg" alt="algebraic reasoning" class="center">
<br>
<p><strong>Desired Capabilities for EO Data.</strong> To build an EO benchmark for VLMs, we focus on three broad categories of capabilities in our initial release: scene understanding, localization and counting, and change detection. Within each category, we construct evaluations based on applications ranging from animal conservation to urban monitoring. Our goals are to (1) evaluate the performance of existing VLMs, (2) provide insights into prompting techniques suitable for repurposing existing VLMs to EO tasks, and (3) implement an interface of data and models for flexible benchmark updates and evaluations of future VLMs. Our categories and tasks are:</p>
<ul>
<li><em>Scene Understanding</em>: To evaluate how VLMs combine high-level information extracted from images with latent knowledge learned through language modeling, we construct three datasets:
<ol>
<li>a new <span style="background-color:#cfe2f3;">aerial landmark recognition</span> dataset to test the model's ability to recognize and geolocate landmarks in the United States;</li>
<li>the <span style="background-color:#cfe2f3;">RSICD</span> dataset to evaluate the model's ability to generate open-ended captions for Google Earth images;</li>
<li>the <span style="background-color:#cfe2f3;">BigEarthNet</span> dataset to probe the model's ability to identify land cover types in medium-resolution satellite images, and</li>
<li>the <span style="background-color:#cfe2f3;">fMoW-WILDS</span> and <span style="background-color:#cfe2f3;">PatternNet</span> datasets to assess the model's ability to classify land use in high-resolution satellite images.</li>
</ol>
</li>
<li><em>Localization & Counting</em>: To evaluate whether VLMs can extract fine-grained information about a specific object and understand its spatial relationship to other objects, we assemble three datasets:
<ol>
<li>the <span style="background-color:#cfe2f3;">DIOR-RSVG</span> dataset to assess Referring Expression Comprehension (REC) abilities, in which the model is required to localize objects based on their natural language descriptions;</li>
<li>the <span style="background-color:#cfe2f3;">NEON-Tree</span>, <span style="background-color:#cfe2f3;">COWC</span>, and <span style="background-color:#cfe2f3;">xBD</span> datasets to assess counting small objects like cluttered trees, cars, and buildings in aerial and satellite images;</li>
<li>the <span style="background-color:#cfe2f3;">aerial animal detection</span> dataset to gauge counting animal populations from tilted aerial images taken by handheld cameras.</li>
</ol>
</li>
<li><em>Change Detection</em>: To evaluate if VLMs can identify differences between multiple images and complete user-specified tasks based on such differences, we repurpose the <span style="background-color:#cfe2f3;">xBD</span> dataset. We show the model two high-resolution images taken before and after a natural disaster and ask it to assign damaged buildings to qualitative descriptions of damage categories.</li>
</ul>
<p>We note that a number of capabilities desired for EO data remain unattainable by current-generation VLMs due to their inability to ingest multi-spectral, non-optical, or multi-temporal images. This is unlikely to be addressed by the vision community while its focus remains on natural images. Furthermore, available VLMs do not yet perform image segmentation, although we expect this to change in the near future.</p>
</div>
</div>
</div>
<div class="content has-text-centered">
<img src="static/images/strength_weakness.svg" alt="Strength and weakness of GPT-4V"/>
<p> GPT-4V has scene understanding abilities but cannot accurately count or localize objects. We only select part of the user prompt and model response for illustration purposes. </p>
</div>
</div>
<!-- <div class="columns is-centered m-6">
<div class="column is-full has-text-centered content">
<h2 class="title is-3">Statistics</h2>
<div id="results-carousel" class="carousel results-carousel">
<div class="box m-5">
<div class="content has-text-centered">
<img src="static/images/VLEO-xx.Jpeg" alt="algebraic reasoning" width="95%"/>
<p> Statistics Figure 1.</p>
</div>
</div>
<div class="box m-5">
<div class="content has-text-centered">
<img src="static/images/xx.Jpeg" alt="arithmetic reasoning" width="40%"/>
<p> Statistics Figure 2</p>
</div>
</div>
<div class="box m-5">
<div class="content has-text-centered">
<img src="static/images/xx.png" alt="arithmetic reasoning" width="80%"/>
<p> Statistics Figure 3</p>
</div>
</div>
</div>
</div>
</div> -->
<!-- <div class="columns is-centered m-6">
<div class="column is-max-desktop has-text-centered">
<h2 class="title is-3" id="visualization">Visualization</h2>
<iframe src="visualizer/explore.html" style="width: 100%;min-height: 100vh; border-radius: 20px;"></iframe>
</div>
</div> -->
</div>
</section>
<!-- RESULTS SECTION -->
<section class="hero is-light is-small">
<div class="hero-body has-text-centered">
<h1 class="title is-1 VLEO-Bench">Experiment Results</h1>
</div>
</section>
<section class="section">
<div class="container">
<div class="columns is-centered has-text-centered">
<!-- <div class="column is-full-width has-text-centered"> -->
<div class="column is-four-fifths">
<h2 class="title is-3">Result Overview</h2>
<div class="content has-text-justified">
<p>Below, we summarize insights from our evaluations, with a focus on GPT-4V, as it is generally the best-performing VLM across Earth observation tasks. We elaborate on the results in Sections Scene Understanding, Localization & Counting, and Change Detection.</p>
<ul>
<li><i>Scene Understanding</i>:
<ol style="margin-left: 2.5em; padding-top: 1pt; list-style-type: none;">
<li>On our new <span style="background-color: #cfe2f3;">aerial landmark recognition</span> task, GPT-4V achieves an overall accuracy of 0.67, surpassing open models by a large margin and demonstrating its comprehensive world knowledge. There appear to be regional disparities, with GPT-4V generally performing better in coastal states. In addition, although GPT-4V sometimes generates sophisticated reasoning paths, the reasoning can be incorrect despite a correct final answer.</li>
<li>On <span style="background-color: #cfe2f3;">RSICD image captioning</span>, GPT-4V achieves a RefCLIPScore of 0.75, which measures both image-text semantic similarity and caption-reference similarity. Although GPT-4V does not achieve high similarity between generated and reference captions, our qualitative assessment is that it generates even more detailed captions than the humans employed in RSICD.</li>
<li>On land cover/land use classification tasks, GPT-4V performance varies depending on image resolution, label ambiguity, and label granularity. On <span style="background-color: #cfe2f3;">fMoW-WILDS</span>, the average F1-score is 0.19; on <span style="background-color: #cfe2f3;">PatternNet</span>, average F1-score is 0.71, and on <span style="background-color: #cfe2f3;">BigEarthNet</span>, average F1-score is 0.38. High performance on PatternNet can be attributed to high image resolution and disambiguated labels. Low performance on fMoW-WILDS is largely due to ambiguous labels, which we discuss in Section Land Cover/Land Use Classification.</li>
</ol>
</li>
<li><i>Localization & Counting</i>:
<ol style="margin-left: 2.5em; padding-top: 1pt; list-style-type: none;">
<li>On <span style="background-color: #cfe2f3;">DIOR-RSVG</span> object localization, GPT-4V obtains a mean intersection-over-union (IoU) of 0.16; only 7.6% of the test images have an IoU > 0.5, while a model that specializes in outputting bounding boxes achieves a mean IoU of 0.68.</li>
<li>While GPT-4V achieves moderate accuracies on the <span style="background-color: #cfe2f3;">COWC</span> vehicle counting and <span style="background-color: #cfe2f3;">xBD</span> building counting tasks, it fails on <span style="background-color: #cfe2f3;">NEON-Tree</span> counting and <span style="background-color: #cfe2f3;">aerial animal detection</span>.</li>
</ol>
</li>
<li><i>Change Detection</i>: On <span style="background-color: #cfe2f3;">xBD</span> change detection, GPT-4V fails to count and categorize the damaged buildings, with a performance score for buildings in the "destroyed" category. Although GPT-4V can count the number of buildings before a disaster with moderate accuracy, it systematically fails to assess the building damage by contrasting before and after images. This systematic failure makes it unusable for disaster relief applications that require counting abilities.</li>
</ul>
</div>
</div>
</div>
</div>
</div>
</section>
<!-------------------------------------------------------------------- RESULTS SECTION -------------------------------------------------------------------->
<div class="columns is-centered m-6">
<div class="column is-full has-text-centered content">
<h2 class="title is-3" id="leaderboard">Leaderboard</h2>
<div class="content"> Incoming </div>
</div>
</div>
<!-------------------------------------------------------------------- Image Type SECTION -------------------------------------------------------------------->
<!-- @PAN TODO: bibtex -->
<section class="section" id="BibTeX">
<div class="container is-max-desktop content">
<h2 class="title is-3 has-text-centered">BibTeX</h2>
<pre><code>
@article{zhang2024vleobench,
title = {Good at captioning, bad at counting: Benchmarking GPT-4V on Earth observation data},
author = {Chenhui Zhang and Sherrie Wang},
year = {2024},
journal = {arXiv preprint arXiv: 2401.17600}
}
</code></pre>
</div>
</section>
<footer class="footer">
<!-- <div class="container"> -->
<div class="content has-text-centered">
</div>
<div class="columns is-centered">
<div class="column is-8">
<div class="content">
<p>
This website is website adapted from <a href="https://nerfies.github.io/">Nerfies</a> and <a href="https://mathvista.github.io/">MathVista</a>, licensed under a <a rel="license"
href="http://creativecommons.org/licenses/by-sa/4.0/">Creative
Commons Attribution-ShareAlike 4.0 International License</a>.
</p>
</div>
</div>
</div>
<!-- </div> -->
</footer>
<script>
function changeButtonText() {
var button = document.getElementById('toggleButton');
if (button.innerHTML.includes("Test Set Leaderboard")) {
button.innerHTML = "<b style='font-size: larger;'>Validation Set Leaderboard</b> (Click to Switch)";
} else {
button.innerHTML = "<b style='font-size: larger;'>Test Set Leaderboard</b> (Click to Switch)";
}
}
document.addEventListener('DOMContentLoaded', function() {
var tables = document.querySelectorAll('table');
tables.forEach(function(table) {
if (!table) return;
var initialRows = Array.from(table.rows).slice(1);
table.addEventListener('click', function(event) {
var clickedCell = event.target.closest('td, th');
if (!clickedCell) return;
var headerRow = clickedCell.parentNode;
var columnIndex = Array.from(headerRow.cells).indexOf(clickedCell);
var type = clickedCell.getAttribute('data-type');
if (headerRow.rowIndex === 0) {
if (columnIndex === 0) {
table.tBodies[0].innerHTML = '';
initialRows.forEach(row => table.tBodies[0].appendChild(row.cloneNode(true)));
}
}
});
});
});
function sortTable(table, column, type, asc) {
var tbody = table.tBodies[0];
var rows = Array.from(tbody.rows);
rows.sort(function(a, b) {
var valA = a.cells[column].textContent;
var valB = b.cells[column].textContent;
if (type === 'number') {
valA = parseFloat(valA);
valB = parseFloat(valB);
}
return asc ? valA - valB : valB - valA;
});
rows.forEach(row => tbody.appendChild(row));
}
// 切换表格的函数
function toggleTables () {
var table1 = document.getElementById('table1');
var table2 = document.getElementById('table2');
table1.classList.toggle('hidden');
table2.classList.toggle('hidden');
}
document.getElementById('toggleButton').addEventListener('click', toggleTables);
const canvas = document.getElementById('difficulty_level_chart');
canvas.style.width = '500px';
canvas.style.height = '120px';
const ctx = document.getElementById('difficulty_level_chart').getContext('2d');
const difficulty_level_chart = new Chart(ctx, {
type: 'bar',
data: {
labels: ['Easy', 'Medium', 'Hard', 'Overall'],
datasets: [{
label: 'Fuyu-8B',
data: [28.9, 27, 26.4, 27.4],
backgroundColor: 'rgba(196, 123, 160, 0.6)',
borderColor: 'rgba(196, 123, 160, 1)',
borderWidth: 1,
hoverBackgroundColor: 'rgba(196, 123, 160, 1)'
},
{
label: 'Qwen-VL-7B',
data: [39.4, 31.9, 27.6, 32.9],
backgroundColor: 'rgba(245, 123, 113, 0.6)',
borderColor: 'rgba(245, 123, 113, 1)',
borderWidth: 1,
hoverBackgroundColor: 'rgba(245, 123, 113, 1)'
},
{
label: 'LLaVA-1.5-13B',
data: [41.3, 32.7, 26.7, 33.6],
backgroundColor: 'rgba(255, 208, 80, 0.6)',
borderColor: 'rgba(255, 208, 80, 1)',
borderWidth: 1,
hoverBackgroundColor: 'rgba(255, 208, 80, 1)'
},
{
label: 'InstructBLIP-T5-XXL',
data: [40.3, 32.3, 29.4, 33.8],
backgroundColor: 'rgba(110, 194, 134, 0.6)',
borderColor: 'rgba(110, 194, 134, 1)',
borderWidth: 1,
hoverBackgroundColor: 'rgba(110, 194, 134, 1)'
},
{
label: 'BLIP-2 FLAN-T5-XXL',
data: [41, 32.7, 28.5, 34],
backgroundColor: 'rgba(255, 153, 78, 0.6)',
borderColor: 'rgba(255, 153, 78, 1)',
borderWidth: 1,
hoverBackgroundColor: 'rgba(255, 153, 78, 1)'
},
{
label: 'GPT-4V',
data: [76.1, 55.6, 31.2, 55.7],
backgroundColor: 'rgba(117, 209, 215, 0.6)',
borderColor: 'rgba(117, 209, 215, 1)',
borderWidth: 1,
hoverBackgroundColor: 'rgba(117, 209, 215, 1)'
}]
},
options: {
scales: {
y: {
beginAtZero: true,
min: 0,
max: 100,
ticks: {
stepSize: 20,
font: {
size: 16
}
}
},
x: {
ticks: {
font: {
size: 16 // 设置X轴字体大小
}
}
}
},
plugins: {
legend: {
labels: {
font: {
size: 16 // 设置标签文字大小
}
}
},
tooltip: {
callbacks: {
label: function(context) {
return context.dataset.label + ': ' + context.parsed.y;
}
}
}
},
onHover: (event, chartElement) => {
event.native.target.style.cursor = chartElement[0] ? 'pointer' : 'default';
}
}
});
document.addEventListener('DOMContentLoaded', function() {
// Data for the "Diagrams" chart
const data_Diagrams = {
labels: ['Fuyu-8B', 'Qwen-VL-7B', 'InstructBLIP-T5-XXL', 'LLaVA-1.5-13B', 'BLIP-2 FLAN-T5-XXL', 'GPT-4V'],
datasets: [{
data: [27.6, 30.1, 31.8, 30.0, 32.0, 46.8],
backgroundColor: ['rgba(196, 123, 160, 0.6)', 'rgba(245, 123, 113, 0.6)', 'rgba(255, 208, 80, 0.6)', 'rgba(110, 194, 134, 0.6)', 'rgba(255, 153, 78, 0.6)', 'rgba(117, 209, 215, 0.6)'],
borderColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,0.4)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)'],
hoverBackgroundColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,1)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)']
}]
};
// "data_Diagrams" chart
new Chart(document.getElementById('chart_Diagrams'), {
type: 'bar',
data: data_Diagrams,
options: {
scales: {
y: {
beginAtZero: true,
min: 0,
max: 100,
ticks: {
stepSize: 20
}
},
x: {
display: false
}
},
plugins: {
legend: {
display: false
},
tooltip: {
}
}
}
});
// "data_Tables" chart
const data_Tables = {
labels: ['Fuyu-8B', 'Qwen-VL-7B', 'InstructBLIP-T5-XXL', 'LLaVA-1.5-13B', 'BLIP-2 FLAN-T5-XXL', 'GPT-4V'],
datasets: [{
data: [26.6, 29.0, 29.8, 27.8, 27.8, 61.8],
backgroundColor: ['rgba(196, 123, 160, 0.6)', 'rgba(245, 123, 113, 0.6)', 'rgba(255, 208, 80, 0.6)', 'rgba(110, 194, 134, 0.6)', 'rgba(255, 153, 78, 0.6)', 'rgba(117, 209, 215, 0.6)'],
borderColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,0.4)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)'],
hoverBackgroundColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,1)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)']
}]
};
new Chart(document.getElementById('chart_Tables'), {
type: 'bar',
data: data_Tables,
options: {
scales: {
y: {
beginAtZero: true,
min: 0,
max: 100,
ticks: {
stepSize: 20
}
},
x: {
display: false
}
},
plugins: {
legend: {
display: false
},
tooltip: {
}
}
}
});
// "data_PlotsAndCharts " chart
const data_PlotsAndCharts = {
labels: ['Fuyu-8B', 'Qwen-VL-7B', 'InstructBLIP-T5-XXL', 'LLaVA-1.5-13B', 'BLIP-2 FLAN-T5-XXL', 'GPT-4V'],
datasets: [{
data: [24.8, 31.8, 36.2, 30.4, 35.8, 55.6],
backgroundColor: ['rgba(196, 123, 160, 0.6)', 'rgba(245, 123, 113, 0.6)', 'rgba(255, 208, 80, 0.6)', 'rgba(110, 194, 134, 0.6)', 'rgba(255, 153, 78, 0.6)', 'rgba(117, 209, 215, 0.6)'],
borderColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,0.4)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)'],
hoverBackgroundColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,1)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)']
}]
};
new Chart(document.getElementById('chart_PlotsAndCharts'), {
type: 'bar',
data: data_PlotsAndCharts ,
options: {
scales: {
y: {
beginAtZero: true,
min: 0,
max: 100,
ticks: {
stepSize: 20
}
},
x: {
display: false
}
},
plugins: {
legend: {
display: false
},
tooltip: {
}
}
}
});
// "data_ChemicalStructures " chart
const data_ChemicalStructures = {
labels: ['Fuyu-8B', 'Qwen-VL-7B', 'InstructBLIP-T5-XXL', 'LLaVA-1.5-13B', 'BLIP-2 FLAN-T5-XXL', 'GPT-4V'],
datasets: [{
data: [25.0, 27.2, 27.1, 26.7, 25.5, 50.6],
backgroundColor: ['rgba(196, 123, 160, 0.6)', 'rgba(245, 123, 113, 0.6)', 'rgba(255, 208, 80, 0.6)', 'rgba(110, 194, 134, 0.6)', 'rgba(255, 153, 78, 0.6)', 'rgba(117, 209, 215, 0.6)'],
borderColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,0.4)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)'],
hoverBackgroundColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,1)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)']
}]
};
new Chart(document.getElementById('chart_ChemicalStructures'), {
type: 'bar',
data: data_ChemicalStructures ,
options: {
scales: {
y: {
beginAtZero: true,
min: 0,
max: 100,
ticks: {
stepSize: 20
}
},
x: {
display: false
}
},
plugins: {
legend: {
display: false
},
tooltip: {
}
}
}
});
// "data_Photographs " chart
const data_Photographs = {
labels: ['Fuyu-8B', 'Qwen-VL-7B', 'InstructBLIP-T5-XXL', 'LLaVA-1.5-13B', 'BLIP-2 FLAN-T5-XXL', 'GPT-4V'],
datasets: [{
data: [27.6, 40.5, 41.4, 44.4, 42.0, 64.2],
backgroundColor: ['rgba(196, 123, 160, 0.6)', 'rgba(245, 123, 113, 0.6)', 'rgba(255, 208, 80, 0.6)', 'rgba(110, 194, 134, 0.6)', 'rgba(255, 153, 78, 0.6)', 'rgba(117, 209, 215, 0.6)'],
borderColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,0.4)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)'],
hoverBackgroundColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,1)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)']
}]
};
new Chart(document.getElementById('chart_Photographs'), {
type: 'bar',
data: data_Photographs ,
options: {
scales: {
y: {
beginAtZero: true,
min: 0,
max: 100,
ticks: {
stepSize: 20
}
},
x: {
display: false
}
},
plugins: {
legend: {
display: false
},
tooltip: {
}
}
}
});
// "data_Paintings " chart
const data_Paintings = {
labels: ['Fuyu-8B', 'Qwen-VL-7B', 'InstructBLIP-T5-XXL', 'LLaVA-1.5-13B', 'BLIP-2 FLAN-T5-XXL', 'GPT-4V'],
datasets: [{
data: [28.7, 57.2, 53.6, 56.3, 52.1, 75.9],
backgroundColor: ['rgba(196, 123, 160, 0.6)', 'rgba(245, 123, 113, 0.6)', 'rgba(255, 208, 80, 0.6)', 'rgba(110, 194, 134, 0.6)', 'rgba(255, 153, 78, 0.6)', 'rgba(117, 209, 215, 0.6)'],
borderColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,0.4)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)'],
hoverBackgroundColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,1)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)']
}]
};
new Chart(document.getElementById('chart_Paintings'), {
type: 'bar',
data: data_Paintings ,
options: {
scales: {
y: {
beginAtZero: true,
min: 0,
max: 100,
ticks: {
stepSize: 20
}
},
x: {
display: false
}
},
plugins: {
legend: {
display: false
},
tooltip: {
}
}
}
});
// "data_GeometricShapes " chart
const data_GeometricShapes = {
labels: ['Fuyu-8B', 'Qwen-VL-7B', 'InstructBLIP-T5-XXL', 'LLaVA-1.5-13B', 'BLIP-2 FLAN-T5-XXL', 'GPT-4V'],
datasets: [{
data: [21.1, 25.3, 21.4, 25.6, 28.3, 40.2],
backgroundColor: ['rgba(196, 123, 160, 0.6)', 'rgba(245, 123, 113, 0.6)', 'rgba(255, 208, 80, 0.6)', 'rgba(110, 194, 134, 0.6)', 'rgba(255, 153, 78, 0.6)', 'rgba(117, 209, 215, 0.6)'],
borderColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,0.4)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)'],
hoverBackgroundColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,1)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)']
}]
};
new Chart(document.getElementById('chart_GeometricShapes'), {
type: 'bar',
data: data_GeometricShapes ,
options: {
scales: {
y: {
beginAtZero: true,
min: 0,
max: 100,
ticks: {
stepSize: 20
}
},
x: {
display: false
}
},
plugins: {
legend: {
display: false
},
tooltip: {
}
}
}
});
// "data_SheetMusic " chart
const data_SheetMusic = {
labels: ['Fuyu-8B', 'Qwen-VL-7B', 'InstructBLIP-T5-XXL', 'LLaVA-1.5-13B', 'BLIP-2 FLAN-T5-XXL', 'GPT-4V'],
datasets: [{
data: [35.2, 33.4, 34.6, 35.8, 34.9, 38.8],
backgroundColor: ['rgba(196, 123, 160, 0.6)', 'rgba(245, 123, 113, 0.6)', 'rgba(255, 208, 80, 0.6)', 'rgba(110, 194, 134, 0.6)', 'rgba(255, 153, 78, 0.6)', 'rgba(117, 209, 215, 0.6)'],
borderColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,0.4)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)'],
hoverBackgroundColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,1)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)']
}]
};
new Chart(document.getElementById('chart_SheetMusic'), {
type: 'bar',
data: data_SheetMusic ,
options: {
scales: {
y: {
beginAtZero: true,
min: 0,
max: 100,
ticks: {
stepSize: 20
}
},
x: {
display: false
}
},
plugins: {
legend: {
display: false
},
tooltip: {
}
}
}
});
// "data_MedicalImages " chart
const data_MedicalImages = {
labels: ['Fuyu-8B', 'Qwen-VL-7B', 'InstructBLIP-T5-XXL', 'LLaVA-1.5-13B', 'BLIP-2 FLAN-T5-XXL', 'GPT-4V'],
datasets: [{
data: [25.4, 29.8, 31.6, 36.4, 29.8, 59.6],
backgroundColor: ['rgba(196, 123, 160, 0.6)', 'rgba(245, 123, 113, 0.6)', 'rgba(255, 208, 80, 0.6)', 'rgba(110, 194, 134, 0.6)', 'rgba(255, 153, 78, 0.6)', 'rgba(117, 209, 215, 0.6)'],
borderColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,0.4)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)'],
hoverBackgroundColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,1)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)']
}]
};
new Chart(document.getElementById('chart_MedicalImages'), {
type: 'bar',
data: data_MedicalImages ,
options: {
scales: {
y: {
beginAtZero: true,
min: 0,
max: 100,
ticks: {
stepSize: 20
}
},
x: {
display: false
}
},
plugins: {
legend: {
display: false
},
tooltip: {
}
}
}
});
// "data_PathologicalImages " chart
const data_PathologicalImages = {
labels: ['Fuyu-8B', 'Qwen-VL-7B', 'InstructBLIP-T5-XXL', 'LLaVA-1.5-13B', 'BLIP-2 FLAN-T5-XXL', 'GPT-4V'],
datasets: [{
data: [26.5, 27.7, 31.2, 35.2, 35.6, 63.6],
backgroundColor: ['rgba(196, 123, 160, 0.6)', 'rgba(245, 123, 113, 0.6)', 'rgba(255, 208, 80, 0.6)', 'rgba(110, 194, 134, 0.6)', 'rgba(255, 153, 78, 0.6)', 'rgba(117, 209, 215, 0.6)'],
borderColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,0.4)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)'],
hoverBackgroundColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,1)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)']
}]
};
new Chart(document.getElementById('chart_PathologicalImages'), {
type: 'bar',
data: data_PathologicalImages ,
options: {
scales: {
y: {
beginAtZero: true,
min: 0,
max: 100,
ticks: {
stepSize: 20
}
},
x: {
display: false
}
},
plugins: {
legend: {
display: false
},
tooltip: {
}
}
}
});
// "data_MicroscopicImages " chart
const data_MicroscopicImages = {
labels: ['Fuyu-8B', 'Qwen-VL-7B', 'InstructBLIP-T5-XXL', 'LLaVA-1.5-13B', 'BLIP-2 FLAN-T5-XXL', 'GPT-4V'],
datasets: [{
data: [27.0, 37.6, 29.2, 36.3, 32.7, 58.0],
backgroundColor: ['rgba(196, 123, 160, 0.6)', 'rgba(245, 123, 113, 0.6)', 'rgba(255, 208, 80, 0.6)', 'rgba(110, 194, 134, 0.6)', 'rgba(255, 153, 78, 0.6)', 'rgba(117, 209, 215, 0.6)'],
borderColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,0.4)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)'],
hoverBackgroundColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,1)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)']
}]
};
new Chart(document.getElementById('chart_MicroscopicImages'), {
type: 'bar',
data: data_MicroscopicImages ,
options: {
scales: {
y: {
beginAtZero: true,
min: 0,
max: 100,
ticks: {
stepSize: 20
}
},
x: {
display: false
}
},
plugins: {
legend: {
display: false
},
tooltip: {
}
}