AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

Injection Without Distortion: Geometrically Constrained Knowledge Enhancement for Vision-Language Models

Zhongze Wu, Xiu Su, Feng Yang, Shan You, Jun Long, Yueyi Luo

AAAI 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Adapting VLMs for zero-shot classification · 0 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 null-space projection to knowledge injection (ablation)HKI knowledge injection · iNatLoc average (Swin-B, IV)mAP50: 76.8 -> 79.9Improved
add null-space projection (ablation)HKI knowledge injection · iNatLoc L1 (Swin-B, IV)mAP50: 62.1 -> 67.5Improved
unconstrained injection (SHiNe) on coarse concepts (ablation)Detic · iNatLoc L1 (Swin-B, IV)mAP50: 64.4 -> 62.1Hurt
protect query concept plus its sub-concepts (hierarchical) vs query-only (ablation)GeCoin · iNatLoc average (Swin-B, IV)mAP50: 78.7 -> 79.9Improved
use fine-grained knowledge (FKI) with projection vs unconstrained (ablation)FKI knowledge injection · iNatLoc average (Swin-B, IV)mAP50: 76.6 -> 79.5Improved
add 20% irrelevant concepts to LLM knowledge (ablation)GeCoin vs SHiNe · iNatLoc average (ResNet-50), GPT-3.5mAP50: GeCoin 51.4 -> 49.5; SHiNe 46.5 -> 43.0Hurt
GeCoin vs SHiNe on ImageNet BREEDS L1GeCoin · ImageNet-1k BREEDS L1top-1 accuracy: 50.4 -> 61.3Improved
GeCoin vs H-CLIP on BREEDS averageGeCoin · ImageNet-1k BREEDS averagetop-1 accuracy: 68.4 -> 68.6No clear effect
GeCoin vs SHiNe on FSOD L3GeCoin · FSOD (Swin-B, IV)mAP50: 66.4 -> 66.5No clear effect
GeCoin on CoDetCoDet · iNatLoc average (ResNet-50)mAP50: 34.4 -> 38.6 (vs SHiNe)Improved
GeCoin on LLM-DetLLM-Det · iNatLoc average (Swin-T)mAP50: 56.7 -> 59.1 (vs SHiNe)Improved

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