AI Paper Atlas

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

CLIP-Adapted Region-to-Text Learning for Generative Open-Vocabulary Semantic Segmentation

Jiannan Ge, Lingxi Xie, Hongtao Xie, Pandeng Li, Sun-Ao Liu, Xiaopeng Zhang, Qi Tian, Yongdong Zhang

ICCV 2025 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary semantic segmentation · 7 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
train the language model rather than keeping it frozen (ablation)CRTNet · P-59 / A-150 / P-459 / A-847mIoU: 47.5 -> 49.9 (P-59), 20.2 -> 23.6 (A-150), 12.3 -> 15.1 (P-459), 5.2 -> 7.9 (A-847)Improved
add CC3M-595K to VG and COCO training data (ablation)CRTNet · ADE-847mIoU: 5.4 -> 7.9Improved
add COCO to VG training data (ablation)CRTNet · ADE-150mIoU: 21.4 -> 21.2 (VG alone vs VG+COCO)Hurt
add VG and COCO region-level data to CC3M-only training (ablation)CRTNet · VOCmIoU: 84.7 -> 91.4Improved
use temperature temp=5 instead of 0.5 (ablation)text-aware feature aggregation · VOCmIoU: 78.4 -> 85.2Improved
raise temp from 5 to 100 (ablation)text-aware feature aggregation · VOCmIoU: 85.2 -> 83.4Hurt
filter 60% of noun phrases from CC3M captions instead of none (ablation)data engine · P-459mIoU: 7.9 -> 9.0Improved
filter 60% of noun phrases instead of none (ablation)data engine · A-150mIoU: 16.8 -> 18.7Improved
increase beam size from 1 to 3 (ablation)CRTNet inference · A-150mIoU: 22.3 -> 23.6Improved
increase beam size from 3 to 5 (ablation)CRTNet inference · A-150mIoU: 23.6 -> 23.1Hurt
raise CC3M proportion from 1:1:1 to 4:1:1 (ablation)training data mix · A-150mIoU: 23.6 -> 22.5Hurt
use FlanT5-Base encoder-decoder instead of OPT-350M (ablation)language model · VOCmIoU: 79.2 -> 90.7Improved

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