AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Rethinking Rotation-Invariant Recognition of Fine-Grained Shapes From the Perspective of Contour Points

Yanjie Xu, Yunzhi Chen, Handing Xu, Tianmu Wang, Yaguan Li, Zhenguo Nie

TPAMI 2025 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use LOA instead of LRA (ablation)contour rotation-invariant network · Kidney retrieval, lambda=1retrieval success rate: 6.65 -> 90.78Improved
use LOA instead of LRA (ablation)contour rotation-invariant network · Kimia99 retrieval, lambda=1retrieval success rate: 18.39 -> 76.01Improved
use LOA instead of LRA with more augmentation (ablation)contour rotation-invariant network · Kimia99 retrieval, lambda=5retrieval success rate: 98.29 -> 96.45Hurt
use LOA instead of LRA (ablation)contour rotation-invariant network · Kidney retrieval, lambda=5retrieval success rate: 80.09 -> 99.33Improved
increase rotation augmentation lambda from 1 to 3Ours · Flavia classificationmean accuracy: 89.14 -> 95.96Improved
increase rotation augmentation lambda from 1 to 5Ours · Kidney retrievalmean retrieval accuracy: 94.20 -> 100.00Improved
increase rotation augmentation lambda from 1 to 5Ours · Liver retrievalmean retrieval accuracy: 65.07 -> 99.49Improved
add noisy shapes as training augmentation (Ours_DA)Ours · contour noise levels 0-5 retrievalrecognition accuracyImproved
use contour-point encoding instead of pixel-based networksOurs vs image-based methods · contour noise robustnessrecognition accuracyHurt
compare contour-point method against RIC-CNN on Flavia classificationOurs · Flavia classificationaccuracy (%): 88.68 -> 97.11Improved
rotation augmentation of training data on rotation-center robustnessOurs · rotation center positionaccuracyMixed
change point-sequence starting point (Type-II rotation)Ours · rotation type testaccuracyNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy