You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: src/paper.mdx
+4Lines changed: 4 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -105,10 +105,14 @@ Most vision pipelines apply planar CNNs that assume a pinhole camera and operate
105
105
106
106
A model is **rotation-equivariant** if rotating its input produces an equivalently rotated output. This is a desirable property for any system where camera orientation may vary at test time. USF achieves both lens-agnostic processing and rotation-equivariance while supporting **plug-and-play** replacement of planar layers in any existing backbone, providing a generic framework for modern vision.
107
107
108
+
<HighlightedSection>
109
+
108
110
## Methodology
109
111
110
112
<InteractiveFrameworkclient:idle />
111
113
114
+
</HighlightedSection>
115
+
112
116
## Results
113
117
114
118
We replace standard planar layers with spherical counterparts while keeping all other aspects of the models and training protocol **identical**. All evaluation is performed in the **planar domain** for consistency. **NR** and **RR** denote non-rotated and randomly rotated settings. Prior spectral-domain spherical CNNs are compared only in the low-resolution MNIST experiment due to their prohibitive cost at higher resolutions.
0 commit comments