Research map / Vision-language and multimodal / Human and embodied modeling
Heterogeneous Uncertainty-Guided Composed Image Retrieval with Fine-Grained Probabilistic Learning
Haomiao Tang, Jinpeng Wang, Minyi Zhao, GuangHao Meng, Ruisheng Luo, Long Chen, Shu-Tao Xia
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 |
|---|---|---|---|
| add probabilistic embeddings to point matching (ablation) | HUG · Fashion-IQ val | average recall: 52.26 -> 55.44 | Improved |
| add component-wise fine-grained contrast (ablation) | HUG · Fashion-IQ val | average recall: 55.44 -> 57.97 | Improved |
| add instance-wise fine-grained contrast (ablation) | HUG · Fashion-IQ val | average recall: 57.97 -> 58.48 | Improved |
| add modality-wise fine-grained contrast (ablation) | HUG · Fashion-IQ val | average recall: 58.48 -> 59.33 | Improved |
| add naive cross-modal uncertainty (ablation) | HUG · Fashion-IQ val | average recall: 59.33 -> 58.57 | Hurt |
| add multi-modal coordination loss (ablation) | HUG · Fashion-IQ val | average recall: 58.57 -> 63.11 | Improved |
| add dynamic weighting instead of static averaging (ablation) | HUG · Fashion-IQ val | average recall: 63.11 -> 63.74 | Improved |
| add probabilistic uncertainty modelling cost (ablation) | HUG · Fashion-IQ val | avg time per query (ms): 7.51 -> 21.35 | Hurt |
| set lambda_Cord to 0.1 rather than larger (ablation) | HUG · Fashion-IQ val | average recall | Improved |
| reduce lambda_FC (ablation) | HUG · Fashion-IQ val | average recall | Hurt |
| use HUG instead of QuRe | HUG · CIRR test | Recall@1: 52.22 vs 51.09 | Mixed |
| use HUG instead of QuRe | HUG · Fashion-IQ val | average recall: 63.04 -> 63.74 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- CoVR — COVR: Collaborative Optimization of VLMs and RL Agent for Visual-Based Control (AAAI 2026) · better on 1 of 1 shared result
- FAME-ViL — FAME-ViL: Multi-Tasking Vision-Language Model for Heterogeneous Fashion Tasks (CVPR 2023) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Composed Image Retrieval with Text Feedback via Multi-grained Uncertainty Regularization (ICLR 2024 · similarity 0.91)
- Instance-Level Composed Image Retrieval (NeurIPS 2025 · similarity 0.87)
- Learning with Noisy Triplet Correspondence for Composed Image Retrieval (CVPR 2025 · similarity 0.87)
- Risk Controlled Image Retrieval (AAAI 2025 · similarity 0.87)
- QuRe: Query-Relevant Retrieval through Hard Negative Sampling in Composed Image Retrieval (ICML 2025 · similarity 0.86)
- Visual Delta Generator with Large Multi-modal Models for Semi-supervised Composed Image Retrieval (CVPR 2024 · similarity 0.86)
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.
