AI Paper Atlas

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

Find Beauty in the Rare: Contrastive Composition Feature Clustering for Nontrivial Cropping Box Regression

Zhiyu Pan, Yinpeng Chen, Jiale Zhang, Hao Lu, Zhiguo Cao, Weicai Zhong

AAAI 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 8 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
Add C2C to CBLNet (ablation)CBLNet · FCDB AllIoU: 0.700 -> 0.718Improved
Add C2C to CBLNet (ablation)CBLNet · FCDB FewIoU: 0.391 -> 0.418Improved
Add C2C to CBLNet (ablation)CBLNet · FCDB AllBDE: 0.075 -> 0.069Improved
Add the boundary feature encoder (ablation)regression baseline · FCDBIoU: 0.692 -> 0.700No clear effect
Increase batch size from 4 to 256 (ablation)C2C · FCDB FewIoU: 0.424 -> 0.471Improved
Increase batch size from 4 to 256 (ablation)C2C · FCDB AllIoU: 0.734 -> 0.750Mixed
Use regressor re-training (RRT)CBLNet baseline · FCDB FewIoU: 0.391 -> 0.416Improved
Use regressor re-training (RRT)CBLNet baseline · FCDB Med.IoU: 0.659 -> 0.653Hurt
Use LDS&FDSCBLNet baseline · FCDB FewIoU: 0.391 -> 0.408Improved
Use LDS&FDSCBLNet baseline · FCDBtraining time: 0.720 -> 1.187Hurt

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