AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Self-guided Semantic Inspection for Zero-Shot Composed Image Retrieval

Jingjing Zhang, Lei Zhang, Zheren Fu, Bo Hu, Zhendong Mao

CVPR 2026 · Vision-language and multimodal › Human and embodied modeling · approach: Composed and text-based image retrieval

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 Contextual Semantic Super-patch (CSS) to baseline (ablation)baseline · FashionIQ valR@10: 29.5 -> 30.1Improved
add Phrase-guided Selective Masking alone to baseline (ablation)baseline · FashionIQ valR@10: 29.5 -> 29.8No clear effect
add Difference-aware Composition alone to baseline (ablation)baseline · FashionIQ valR@10: 29.5 -> 29.3No clear effect
add PSM and DAC on top of CSS (ablation)DiffComp · FashionIQ valR@10: 30.1 -> 32.6Improved
add PSM and DAC on top of CSS (ablation)DiffComp · CIRRR@1: 29.5 -> 32.4Improved
increase super-patch grid from 2x2 to 4x4 (ablation)DiffComp · FashionIQ valR@10: 31.9 -> 32.6Improved
use overly coarse 8x8 super-patch grid instead of 4x4 (ablation)DiffComp · FashionIQ valR@10: 32.6 -> 29.6Hurt
use K-Means clustering instead of 4x4 grid for super-patches (ablation)DiffComp · FashionIQ / CIRRR@10 / R@1: FashionIQ 32.6 -> 31.6; CIRR 32.4 -> 32.8Mixed
use random cropping instead of phrase-guided masking (ablation)DiffComp · FashionIQ valR@10: 32.6 -> 29.8Hurt
use soft differentiable masking instead of hard masking (ablation)DiffComp · FashionIQ valR@10: 30.2 -> 32.6Improved
use phrase-level instead of sentence-level guidance (ablation)DiffComp · CIRRR@1: 32.0 -> 32.4Improved
replace SlerpTAT-style global fusion approach with DiffComp (CLIP)SlerpTAT · CIRCO testmAP@50: 20.58 -> 20.30No clear effect

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