AI Paper Atlas

Research map / Continual learning / Class-incremental

Endpoints Weight Fusion for Class Incremental Semantic Segmentation

Jia-Wen Xiao, Chang-Bin Zhang, Jiekang Feng, Xialei Liu, Joost van de Weijer, Ming-Ming Cheng

CVPR 2023 · Continual learning › Class-incremental · approach: Unknown-class mining for incremental segmentation · 51 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
Fuse the old and new task endpoint weights with dynamic αtMiB on PASCAL VOC 2012 15-1 · PASCAL VOC 2012 15-1mIoU (%): 32.2 -> 65.5Improved
Fuse the old and new task endpoint weights with dynamic αtPLOP on PASCAL VOC 2012 10-1 · PASCAL VOC 2012 10-1mIoU (%): 30.5 -> 51.9Improved
Fuse the old and new task endpoint weights with dynamic αtMiB on ADE20K 100-5 · ADE20K 100-5mIoU (%): 25.9 -> 32.1Improved
Add EWF to SSULSSUL on PASCAL VOC 2012 15-1 · PASCAL VOC 2012 15-1mIoU (%): 67.6 -> 68.6Improved
Replace EWF with EMA fusion (ablation)MiB on PASCAL VOC 2012 15-1 · PASCAL VOC 2012 15-1mIoU (%): 65.6 -> 37.3Hurt
Replace EWF with prediction-level model ensemble (ablation)MiB on PASCAL VOC 2012 15-1 · PASCAL VOC 2012 15-1mIoU (%): 65.6 -> 37.2Hurt
Remove model fusion (ablation)MiB on PASCAL VOC 2012 15-1 · PASCAL VOC 2012 15-1mIoU (%): 65.6 -> 32.2Hurt
Replace dynamic αt with fixed α=0.2 (ablation)MiB+EWF · PASCAL VOC 2012 settings 15-1, 10-1, and 5-3average mIoU (%): 51.6 -> 47.7Hurt
Replace dynamic αt with fixed α=0.4 (ablation)MiB+EWF · PASCAL VOC 2012 settings 15-1, 10-1, and 5-3average mIoU (%): 51.6 -> 48.9Hurt
Replace dynamic αt with fixed α=0.6 (ablation)MiB+EWF · PASCAL VOC 2012 settings 15-1, 10-1, and 5-3average mIoU (%): 51.6 -> 46.3Hurt
Replace dynamic αt with fixed α=0.8 (ablation)MiB+EWF · PASCAL VOC 2012 settings 15-1, 10-1, and 5-3average mIoU (%): 51.6 -> 40.2Hurt
Fuse endpoint weights with dynamic αtMiB on PASCAL VOC 2012 19-1 · PASCAL VOC 2012 19-1mIoU (%): 74.7 -> 74.7No clear effect

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