AI Paper Atlas

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

Self-Training Boosted Multi-Factor Matching Network for Composed Image Retrieval

Haokun Wen, Xuemeng Song, Jianhua Yin, Jianlong Wu, Weili Guan, Liqiang Nie

TPAMI 2023 · Vision-language and multimodal › Human and embodied modeling · approach: Composed and text-based image retrieval · 35 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
use multiple latent factor tokens instead of one (U=1) (ablation)LIMN · FashionIQ-AvgR@10: 51.77 -> 55.91Improved
use multiple latent factor tokens instead of one (U=1) (ablation)LIMN · CIRRAvg recall: 68.70 -> 72.19Improved
add batch-based classification loss on latent factor tokens (ablation)LIMN · FashionIQ-AvgR@10: 54.43 -> 55.91Improved
add batch-based classification loss on latent factor tokens (ablation)LIMN · CIRRAvg recall: 69.80 -> 72.19Improved
use CLIP global features to derive latent factor tokens (ablation)LIMN · FashionIQ-AvgR@10: 43.92 -> 55.91Improved
use CLIP global features to derive latent factor tokens (ablation)LIMN · CIRRAvg recall: 60.91 -> 72.19Improved
add filtering of pseudo triplets by LIMN score (ablation)LIMN+ · FashionIQ-AvgR@10: 57.17 -> 57.43Improved
add filtering of pseudo triplets by LIMN score (ablation)LIMN+ · CIRRAvg recall: 72.03 -> 72.35Improved
add iterative dual self-training to LIMNLIMN · FashionIQ-AvgR@10: 55.91 -> 57.43Improved
add iterative dual self-training to LIMNLIMN · ShoesR@10: 68.20 -> 68.37Improved
add iterative dual self-training to LIMNLIMN · CIRRR@1: 43.64 -> 43.33Hurt
add iterative dual self-training to LIMNLIMN · CIRRAvg recall: 72.19 -> 72.35No 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