AI Paper Atlas

Research map / Continual learning / Class-incremental

CoinSeg: Contrast Inter- and Intra- Class Representations for Incremental Segmentation

Zekang Zhang, Guangyu Gao, Jianbo Jiao, Chi Harold Liu, Yunchao Wei

ICCV 2023 · Continual learning › Class-incremental · approach: Unknown-class mining for incremental segmentation · 27 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
replace ResNet101 with Swin-B backbone (freeze strategy) (ablation)CoinSeg · Pascal VOC 2012 15-1mIoU (all): 63.3 -> 70.5Improved
replace freeze strategy with flexible initial learning rate only (no regularization) (ablation)CoinSeg Swin-B · Pascal VOC 2012 15-1mIoU (all): 70.5 -> 66.7Hurt
add feature distillation loss to flexible learning rate (ablation)CoinSeg · Pascal VOC 2012 15-1mIoU (all): 66.7 -> 70.3Improved
add logit distillation (ablation)CoinSeg · Pascal VOC 2012 15-1mIoU (all): 70.3 -> 71.6Improved
add inter-class contrastive loss (ablation)CoinSeg · Pascal VOC 2012 15-1mIoU (all): 71.6 -> 72.4Improved
add intra-class contrastive loss with mask proposals (ablation)CoinSeg · Pascal VOC 2012 15-1mIoU (all): 72.4 -> 75.5Improved
increase number of mask proposals N from 50 to 100 to 200 (ablation)intra-class contrastive loss · Pascal VOC 2012 15-1mIoU (all): 74.2 -> 75.5 -> 76.1Improved
apply flexible tuning instead of freeze to MicroSeg (ablation)MicroSeg · Pascal VOC 2012 15-1mIoU (all): 71.0 -> 72.3 (ResNet101); 69.8 -> 70.4 (Swin-B)Improved
use CoinSeg versus MicroSeg in few-base-class long-term scenarioclass-incremental segmentation · Pascal VOC 2012 2-2mIoU (all): 46.5 -> 64.3Improved
add memory sampling (CoinSeg-M) (ablation)CoinSeg · Pascal VOC 2012 15-1mIoU (all): 75.5 -> 79.6Improved
CoinSeg versus memory-based MicroSeg-M on novel class in 19-1CoinSeg-M · Pascal VOC 2012 19-1mIoU (class 20): 62.4 -> 52.6Hurt

Later papers that compared with this method

2 later accepted papers report CoinSeg as a baseline in their results tables; 2 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