AI Paper Atlas

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

COSTARR: Consolidated Open Set Technique with Attenuation for Robust Recognition

Ryan Rabinowitz, Steve Cruz, Walter Scheirer, Terrance E. Boult

ICCV 2025 · Label-efficient and robust learning › Recognition and long-tail · approach: Loss design and classifier theory · 1 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
score with COSTARR (pre- plus post-attenuation features and logit) instead of PostMaxpretrained ImageNet-1K classifiers · OOSA, unknown NINCO, ResNet-50OOSA: 0.623 -> 0.693Improved
score with COSTARR instead of PostMaxHiera-H · OOSA, unknown NINCOOOSA: 0.758 -> 0.788Improved
score with COSTARR instead of PostMaxConvNeXtV2-H · OOSA, unknown iNatOOSA: 0.850 -> 0.856Improved
use COSTARR instead of PostMaxResNet-50 · AUOSCR, unknown NINCOAUOSCR: 0.624 -> 0.699Improved
add pre-attenuation features F to Hadamard-only similarity (ablation)COSTARR · AUOSCR, ResNet-50, NINCOAUOSCR: 0.365 -> 0.699Improved
add post-attenuation Hadamard features H to features-only similarity (ablation)COSTARR · AUOSCR, ResNet-50, NINCOAUOSCR: 0.681 -> 0.699Improved
scale by normalized logit and use it to select the class (ablation)COSTARR · AUOSCR, ResNet-50, NINCOAUOSCR: 0.690 -> 0.699Improved
scale with globally normalized logit instead of softmax (ablation)COSTARR · AUOSCR, ResNet-50, TexturesAUOSCR: 0.725 -> 0.755Improved
use logit scaling in addition to concatenated F and H on Textures (ablation)COSTARR · AUOSCR, ResNet-50, TexturesAUOSCR: 0.756 -> 0.755No clear effect
score with COSTARR instead of NNGuide/SCALE OOD post-processorsResNet-50 · OOSA, unknown NINCOOOSA: NNGuide 0.445, SCALE 0.555 -> 0.693Improved

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