AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

PCA-Seg: Revisiting Cost Aggregation for Open-Vocabulary Semantic and Part Segmentation

Jianjian Yin, Tao Chen, Yi Chen, Gensheng Pei, Xiangbo Shu, Yazhou Yao, Fumin Shen

CVPR 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary semantic segmentation · 0 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 serial spatial-then-class aggregation with parallel aggregation (ablation)PCA-Seg (ViT-B/16) · A-150mIoU: 36.3 -> 38.1Improved
replace serial with parallel aggregation (ablation)PCA-Seg (ViT-B/16) · PAS-20bmIoU: 81.3 -> 82.7Improved
add cost aggregation (serial) to the cost volume (ablation)CAT-Seg-style model · A-150mIoU: 34.4 -> 36.3Improved
parallelize aggregation with a single conv (no EPL/FOD) (ablation)DeCLIP-style serial model · PAS-20bmIoU: 81.3 -> 81.1No clear effect
add EPL module to the parallel baseline (ablation)PCA-Seg · A-150mIoU: 36.4 -> 37.2Improved
add FOD strategy to the parallel baseline (ablation)PCA-Seg · A-150mIoU: 36.4 -> 36.9Improved
add both EPL and FOD to the parallel baseline (ablation)PCA-Seg · A-150mIoU: 36.4 -> 38.1Improved
add EPL and FOD to a serial architecture (ablation)DeCLIP-style serial model · A-150mIoU: 36.3 -> 36.7Improved
use coefficient mapper instead of convolution for expert integration (ablation)PCA-Seg · PC-59mIoU: 60.7 -> 61.2Improved
use coefficient mapper instead of average/addition fusion (ablation)PCA-Seg · PC-59mIoU: 60.9 -> 61.2Improved
increase expert blocks from 1 to 4 (ablation)PCA-Seg · A-150mIoU: 36.8 -> 37.2Improved
increase expert blocks from 4 to 5 (ablation)PCA-Seg · A-150mIoU: 37.2 -> 36.9Hurt

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