atlas

Research map / Continual learning / Class-incremental

Saving 100x Storage: Prototype Replay for Reconstructing Training Sample Distribution in Class-Incremental Semantic Segmentation

NeurIPS 2023 · Continual learning › Class-incremental · approach: Unknown-class mining for incremental segmentation · 6 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 prototype replay (ablation)STAR · VOC 2012 overlapped 15-1mIoU all: 70.3 -> 72.6Helped
add background repetition (ablation)STAR · VOC 2012 overlapped 15-1mIoU all: 68.1 -> 72.6Helped
add OCFM loss (ablation)STAR · VOC 2012 overlapped 15-1mIoU all: 31.4 -> 72.6Helped
add SAD loss (ablation)STAR · VOC 2012 overlapped 15-1mIoU all: 71.6 -> 72.6Helped
prototype replay instead of 100 stored raw images (DKD-M)STAR vs DKD-M · ADE20K overlapped 100-50mIoU all: 36.0 -> 36.4Helped
add 50 raw images to STARSTAR · VOC 2012 overlapped 15-1mIoU all: 72.6 -> 73.8Helped

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