AI Paper Atlas

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

Learning to Compose: Revisiting Proxy Task Design for Zero-Shot Composed Image Retrieval

Jingjing Zhang, Lei Zhang, Zheren Fu, Zhendong Mao

ECCV 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Attribute-based zero-shot learning · 1 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 text-anchored visual aggregation to global image+text baseline (ablation)FoCo · Ablation CIRR test (ViT-L/14)Recall@1: 12.4 -> 25.8Improved
add context-conditioned completion on top of aggregation (ablation)FoCo · Ablation CIRR test (ViT-L/14)Recall@1: 25.8 -> 34.5Improved
use completion module with coarse patch masking only (ablation)FoCo · Ablation CIRR test (ViT-L/14)Recall@1: 12.4 -> 22.2Improved
use multi-positive cross-instance contrastive loss instead of InfoNCE (ablation)FoCo · Ablation CIRR test (ViT-L/14)Recall@1: 33.1 -> 34.5Improved
use cross-instance negatives instead of intra-image negatives (aggr) (ablation)FoCo · Ablation CIRR test (ViT-L/14)Recall@1: 31.0 -> 34.5Improved
keep aggregation loss during joint training (ablation)FoCo · Ablation CIRR test (ViT-L/14)Recall@1: 33.2 -> 34.5Improved
use LLM decomposition instead of rule-based extraction (ablation)FoCo · Ablation CIRR test (ViT-L/14)Recall@1: 30.7 -> 34.5Improved
use multiple local captions (K>1) instead of one (ablation)FoCo · Ablation CIRR test (ViT-L/14)Recall@1: 32.6 -> 34.5Improved
use text-guided query with global visual feature (ablation)FoCo · Ablation CIRR test (ViT-L/14)Recall@1: 33.5 -> 34.5Improved
use cross-attention instead of dot-product attention (ablation)FoCo · Ablation CIRR test (ViT-L/14)Recall@1: 33.0 -> 34.5Improved
use Transformer blocks in completion module (ablation)FoCo · Ablation FashionIQ val (avg)Recall@10: 27.5 -> 31.5Improved
increase local captions K beyond 4 (K>=6) (ablation)FoCo · CIRCO testmAPHurt

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