AI Paper Atlas

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

ClearCLIP: Decomposing CLIP Representations for Dense Vision-Language Inference

Mengcheng Lan, Chaofeng Chen, Yiping Ke, Xinjiang Wang, Litong Feng, Wayne Zhang

ECCV 2024 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary semantic segmentation · 90 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
remove the residual connection in the last transformer block (ablation)CLIP ViT-B/16 · 5 datasets without backgroundmIoU (Avg.): 27.3 -> 33.7Improved
remove the FFN alone in the last block (ablation)CLIP ViT-B/16 · 5 datasets without backgroundmIoU (Avg.): 27.3 -> 25.9Hurt
remove both residual connection and FFN (ablation)CLIP ViT-B/16 · 5 datasets without backgroundmIoU (Avg.): 33.7 -> 37.5Improved
use q-q self-self attention instead of q-k attention with residual and FFN removed (ablation)ClearCLIP · 5 datasets without backgroundmIoU (Avg.): 27.6 -> 37.5Improved
q-q and k-k self-self attention on larger CLIP-L/14 without removing residual (ablation)CLIP-L/14 · 5 datasets without backgroundmIoUHurt
increase scaling factor alpha of attention output over residual (ablation)CLIP · 5 datasets without backgroundmIoUImproved
ClearCLIP vs SCLIP on ViT-L/14CLIP ViT-L/14 · 5 datasets without backgroundmIoU (Avg.): 23.6 -> 34.5Improved
ClearCLIP vs SCLIP on ViT-B/16 with background classCLIP ViT-B/16 · VOC21mIoU: SCLIP 59.1 vs ClearCLIP 51.8 (SCLIP* reproduced 51.4)Mixed
ClearCLIP vs TCL (weakly supervised) with background classCLIP ViT-B/16 · 3 datasets with backgroundmIoU (Avg.): 35.3 -> 39.1Improved
ClearCLIP on ViT-B/16 vs ViT-L/14 backboneClearCLIP · 5 datasets without backgroundmIoU (Avg.): 37.5 -> 34.5Hurt

Later papers that compared with this method

13 later accepted papers report ClearCLIP as a baseline in their results tables; 13 of them report a better number on most of the results they share with it.

5 more not listed.

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