Research map / Label-efficient and robust learning / Test-time adaptation
Duplex Rewards Optimization for Test-Time Composed Image Retrieval
Haoliang Zhou, Feifei Zhang, Changsheng Xu
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 changed | Where | Measured | Effect |
|---|---|---|---|
| replace CMS with top-k sampling (ablation) | TT-RLDR · FashionIQ avg / CIRR | R@10 / R@1: 26.62 -> 24.89 (FashionIQ R@10 without CMS) | Improved |
| use only reference rewards (ablation) | TT-RLDR · FashionIQ avg | R@10: 25.67 -> 26.62 (adding endogenous rewards) | Improved |
| use only endogenous rewards (ablation) | TT-RLDR · FashionIQ avg | R@10: 25.67 -> 23.42 (ER-only vs RR-only) | Hurt |
| use larger reference reward model (ablation) | TT-RLDR · FashionIQ avg | R@10: 26.62 -> 28.26 (C-G14 reward) | Improved |
| use lighter reward model CLIP-B16 (ablation) | TT-RLDR · FashionIQ avg | R@10: 26.62 -> 25.15 | Hurt |
| use BLIP2 or ALBEF backbone (ablation) | TT-RLDR · FashionIQ avg | R@10: 26.62 -> 22.34 (BLIP2), 20.48 (ALBEF) | Hurt |
| use CLIP-L/14 backbone instead of B/16 (ablation) | TT-RLDR · CIRR | R@10 / R@50: 71.98 -> 72.07 R@10; 91.89 -> 91.74 R@50 | No clear effect |
| TT-RLDR (C-B16) versus other TTA methods | TT-RLDR · CIRR | R@1: 24.54 -> 27.91 (vs RLCF) | Improved |
| TT-RLDR (C-B16) versus RLCF on COCO | TT-RLDR · COCO | R@10: 31.85 -> 34.01 | Improved |
Closest papers by meaning
- ConText-CIR: Learning from Concepts in Text for Composed Image Retrieval (CVPR 2025 · similarity 0.88)
- Reason-before-Retrieve: One-Stage Reflective Chain-of-Thoughts for Training-Free Zero-Shot Composed Image Retrieval (CVPR 2025 · similarity 0.88)
- Generative Zero-Shot Composed Image Retrieval (CVPR 2025 · similarity 0.88)
- Visual Delta Generator with Large Multi-modal Models for Semi-supervised Composed Image Retrieval (CVPR 2024 · similarity 0.87)
- Sentence-level Prompts Benefit Composed Image Retrieval (ICLR 2024 · similarity 0.87)
- Instance-Level Composed Image Retrieval (NeurIPS 2025 · similarity 0.87)
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.
