AI Paper Atlas

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

CLIPer: Hierarchically Improving Spatial Representation of CLIP for Open-Vocabulary Semantic Segmentation

Lin Sun, Jiale Cao, Jin Xie, Xiaoheng Jiang, Yanwei Pang

ICCV 2025 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary semantic segmentation · 15 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 early-layer fusion to baseline (ablation)CLIPer baseline · VOCmIoU: 51.2 -> 61.2Improved
add fine-grained compensation (Stable Diffusion attention) to baseline (ablation)CLIPer baseline · VOCmIoU: 51.2 -> 62.8Improved
add both early-layer fusion and fine-grained compensation (ablation)CLIPer baseline · VOCmIoU: 51.2 -> 69.8Improved
use early-layer fused attention instead of query-query attention (ablation)CLIPer last-layer attention · VOCmIoU: 50.1 -> 58.6Improved
feed early-layer embeddings to last layer with early-layer attention (ablation)CLIPer · VOCmIoU: 58.6 -> 61.2Improved
add early-layer embeddings to value-value attention (ablation)value-value attention · VOCmIoU: 51.2 -> 54.8Improved
fuse Stable Diffusion heads by matrix multiplication instead of single head (ablation)fine-grained compensation · VOCmIoU: 65.3 -> 69.8Improved
average Stable Diffusion heads instead of multiplying (ablation)fine-grained compensation · VOCmIoU: 69.8 -> 64.9Hurt
add fine-grained compensation (diffusion) to CLIPer* (ablation)CLIPer* · VOC inference timetime (ms): 47 -> 192Hurt
CLIPer versus CaR on VOC20 with ViT-LCLIPer · VOC20mIoU: 91.4 -> 90.0Hurt

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