Research map / Vision-language and multimodal / Cross-modal learning
FUSE: Frequency-domain Unification and Spectral Energy Alignment for Multi-modal Object Re-Identification
Xuanhao Qi, Tom H. Luan, Yukang Zhang, Jinkai Zheng, su zhou, Shuwei Li, Lei Tan
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 Cross-Modal Alignment Module (CAM) (ablation) | shared ViT baseline · RGBNT201 | mAP: 76.0 -> 77.2 | Improved |
| add Cross-Modal Alignment Module (CAM) (ablation) | shared ViT baseline · RGBNT201 | Rank-1: 77.8 -> 80.4 | Improved |
| add Spectral Decomposition Module (SDM) (ablation) | shared ViT baseline · RGBNT201 | mAP: 76.0 -> 79.7 | Improved |
| add Spectral Decomposition Module (SDM) (ablation) | shared ViT baseline · RGBNT201 | Rank-1: 77.8 -> 82.1 | Improved |
| add CAM on top of SDM (ablation) | SDM model · RGBNT201 | mAP: 79.7 -> 80.8 | Improved |
| use all three frequency bands (0.3, 0.3, 0.3) instead of low band only (ablation) | SDM · RGBNT201 | mAP: 75.4 -> 79.7 | Improved |
| use mid band only instead of low band only (ablation) | SDM · RGBNT201 | mAP: 75.4 -> 72.2 | Hurt |
| add frequency consistency loss with lambda_freq=0.1 (ablation) | FUSE · RGBNT201 | mAP: 80.8 -> 81.4 | Improved |
| add frequency consistency loss with lambda_freq=0.1 (ablation) | FUSE · RGBNT201 | Rank-1: 84.1 -> 86.1 | Improved |
| increase lambda_freq from 0.1 to 0.3 (ablation) | FUSE · RGBNT201 | mAP: 81.4 -> 79.9 | Hurt |
| use kernel size 7,7,7 instead of 3,3,3 (ablation) | FUSE · RGBNT201 | mAP: 81.4 -> 79.3 | Hurt |
| use mixed kernel sizes 3,5,7 instead of 3,3,3 (ablation) | FUSE · RGBNT201 | mAP: 81.4 -> 78.8 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- IDEA — IDEA: Inverted Text with Cooperative Deformable Aggregation for Multi-modal Object Re-Identification (CVPR 2025) · better on 6 of 6 shared results
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
- Multi-Modal Object Re-identification via Sparse Mixture-of-Experts (ICML 2025 · similarity 0.88)
- Magic Tokens: Select Diverse Tokens for Multi-modal Object Re-Identification (CVPR 2024 · similarity 0.87)
- TOP-ReID: Multi-Spectral Object Re-identification with Token Permutation (AAAI 2024 · similarity 0.87)
- UGG-ReID: Uncertainty-Guided Graph Model for Multi-Modal Object Re-Identification (NeurIPS 2025 · similarity 0.87)
- DeMo: Decoupled Feature-Based Mixture of Experts for Multi-Modal Object Re-Identification (AAAI 2025 · similarity 0.86)
- MDReID: Modality-Decoupled Learning for Any-to-Any Multi-Modal Object Re-Identification (NeurIPS 2025 · 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.
