AI Paper Atlas

Research map / Continual learning / Class-incremental

ALIFE: Adaptive Logit Regularizer and Feature Replay for Incremental Semantic Segmentation

Youngmin Oh, Donghyeon Baek, Bumsub Ham

NeurIPS 2022 · Continual learning › Class-incremental · approach: Unknown-class mining for incremental segmentation · 10 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 feature replay with rotation matrices (ALIFE-M vs ALIFE)ALIFE · ADE20K 100-50(1)hIoU: 29.83 -> 30.28Improved
add feature replay with rotation matricesALIFE · VOC 16-5(5)hIoU: 45.29 -> 48.89Improved
replace CCE/CKD (MiB) with ALIMiB · ADE20K 100-50(1)hIoU: 24.12 -> 29.83Improved
add ALI to CE loss (ablation)ALIFE · VOC 16-5(1)hIoU: 9.74 -> 60.02Improved
add KD on labeled regions to CE+ALI (ablation)ALIFE · VOC 16-5(1)hIoU: 60.02 -> 62.50Improved
apply KD on unlabeled regions too (ablation)ALIFE · VOC 16-5(1)hIoU: 60.02 -> 59.97Hurt
apply KD on all regions instead of labeled only (ablation)ALIFE · VOC 16-5(1)hIoU: 62.50 -> 61.12Hurt
pseudo-label unlabeled regions in classifier fine-tuning (FL) (ablation)ALIFE step 3 · VOC 16-5(1)hIoU: 60.26 -> 61.29Improved
add 1K memorized features per previous category (ablation)ALIFE step 3 · VOC 16-5(1)hIoU: 61.29 -> 64.17Improved
add ALI in step 3 without memory (ablation)ALIFE step 3 · VOC 16-5(1)hIoU: 61.29 -> 62.78Improved
ALIFE-M vs SSUL-MALIFE-M · VOC 16-5(5)hIoU: 48.89 vs 60.30Hurt

Later papers that compared with this method

1 later accepted paper reports ALIFE as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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