AI Paper Atlas

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

CP-CLIP: Customized Parameter Generation for Open-vocabulary Semantic Segmentation

Zelin Peng, Zhengqin Xu, Feilong Tang, Wei Shen

AAAI 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary semantic segmentation · 2 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 orthogonal adaptation (fixed Gaussian beta) to CP-CLIP (ablation)CP-CLIP (ViT-B/16) · A-847mIoU: 11.5 -> 12.8Improved
add customized parameter generator conditioned on local visual features (ablation)CP-CLIP (ViT-B/16) · A-847mIoU: 11.9 -> 12.8Improved
add customized parameter generator conditioned on local visual features (ablation)CP-CLIP (ViT-B/16) · A-150mIoU: 31.9 -> 32.5Improved
freeze beta instead of training it (ablation)CP-CLIP (ViT-B/16) · A-847mIoU: 11.1 -> 12.8Improved
also fine-tune the image encoder (vs text only) (ablation)CP-CLIP (ViT-B/16) · A-847mIoU: 11.2 -> 12.8Improved
fine-tune CLIP text encoder with generated parameters (vs image only) (ablation)CP-CLIP (ViT-B/16) · A-847mIoU: 10.4 -> 12.8Improved
use CP-CLIP instead of plain LoRA (ablation)LoRA (ViT-B/16) · A-847mIoU: 11.4 -> 12.8Improved
increase generator layers M from 3 to 4 (ablation)CP-CLIP (ViT-B/16) · A-847mIoU: 12.8 -> 12.7No clear effect
increase rank r from 32 to 64 (ablation)CP-CLIP (ViT-B/16) · A-847mIoU: 12.8 -> 12.6No clear effect
use high-level (layer 12) instead of layer 1 visual features as condition (ablation)CP-CLIP (ViT-B/16) · A-847mIoU: 11.6 -> 12.8Improved
replace CAT-Seg with CP-CLIPCAT-Seg (ViT-B/16) · A-847mIoU: 12.0 -> 12.8Improved
replace CAT-Seg with CP-CLIPCAT-Seg (ViT-B/16) · PAS-20bmIoU: 77.3 -> 77.1Hurt

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