AI Paper Atlas

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

Exploring Open-Vocabulary Semantic Segmentation from CLIP Vision Encoder Distillation Only

Jun Chen, Deyao Zhu, Guocheng Qian, Bernard Ghanem, Zhicheng Yan, Chenchen Zhu, Fanyi Xiao, Sean Chang Culatana, Mohamed Elhoseiny

ICCV 2023 · Detection and segmentation › Open-set and few-shot detection · approach: Zero-shot segmentation and detection · 55 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
add multi-scale (2x2,3x3,4x4) CLIP feature distillation (ablation)ZeroSeg · PASCAL VOC 2012 (zero-shot)mIoU: 21.1 -> 28.5Improved
add segment matching loss (ablation)ZeroSeg base · PASCAL VOC 2012 (zero-shot)mIoU: 21.1 -> 38.6Improved
add segment matching loss to multi-scale model (ablation)ZeroSeg · PASCAL VOC 2012 (zero-shot)mIoU: 28.5 -> 40.8Improved
use all grid scales 1x1+2x2+3x3+4x4 instead of 1x1+3x3 (ablation)ZeroSeg · PASCAL VOC 2012 (zero-shot)mIoU: 40.2 -> 40.8Improved
use 60% encoder mask ratio instead of 0% (ablation)ZeroSeg · PASCAL VOC 2012 (zero-shot)mIoU: 35.6 -> 40.8Improved
raise mask ratio from 60% to 70% (ablation)ZeroSeg · PASCAL VOC 2012 (zero-shot)mIoU: 40.8 -> 33.3Hurt
train on ImageNet-1K instead of CC3M+COCOZeroSeg · PASCAL VOC 2012 (zero-shot)mIoU: 37.3 -> 40.8Improved
scale training data to CC12M+IN-1KZeroSeg · PASCAL VOC 2012 (zero-shot)mIoU: 40.8 -> 42.9Improved
replace text-supervised GroupViT with CLIP-vision-distilled ZeroSegopen-vocabulary segmentation · Human study, 1000-class vocabularyvotes: 323/1000 -> 677/1000Improved
replace GroupViT with ZeroSeg for computetraining cost · Training cost (V100)GPU hours: ~768 -> ~84Improved
ZeroSeg (IN-1K) versus GroupViT (CC12M+YFCC)PASCAL VOC / Context / COCO · COCO (zero-shot)mIoU: 24.3 -> 20.2Hurt

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