STaG: Human-Annotation-Free Unsupervised Domain Adaptation for Text-Based Person Retrieval
Organizations: School of Computer Science and Technology, Soochow University, Suzhou, China · School of Computer Science, Wuhan University, Wuhan, China
Abstract
Real-world deployment of Text-Based Person Retrieval (TBPR) is bottlenecked by the absence of textual annotations in new domains. Existing Unsupervised Domain Adaptation (UDA-TBPR) methods still assume access to target-domain human-written annotations (albeit unpaired with images), limiting their practicality. We consider a more practical setting: human-annotation-free UDA-TBPR, with labeled image-text data in the source domain and annotation-free, unlabeled images in the target domain. This setting introduces two core challenges: the absence of cross-modal alignment in the target domain, and visual domain shifts from source to target. To tackle these, we propose STaG, a dual-path framework comprising Style-Agnostic Text Alignment (SATA) and Heterogeneous Graph Memory Alignment (HGMA). Specifically, SATA leverages source-domain data to decouple identity-discriminative semantics from machine-generated stylistic artifacts, establishing robust cross-modal alignment for the target domain. Meanwhile, HGMA exploits cross-domain semantic neighborhoods via a memory-based graph to learn domain-invariant visual features. Ultimately, STaG achieves state-of-the-art performance across three benchmarks under this realistic setting.
Figures & tables
| Method | Source: CUHK-PEDES | Source: ICFG-PEDES | |||||||||||||||
| ICFG-PEDES | RSTPReid | CUHK-PEDES | RSTPReid | ||||||||||||||
| R@1 | R@5 | R@10 | mAP | R@1 | R@5 | R@10 | mAP | R@1 | R@5 | R@10 | mAP | R@1 | R@5 | R@10 | mAP | ||
| IVT [ 45 ] | 27.49 | 47.80 | 57.09 | 16.03 | 39.35 | 67.60 | 76.85 | 30.70 | 22.63 | 42.29 | 52.36 | 19.85 | 43.70 | 65.10 | 75.55 | 37.65 | |
| POUF [ 48 ] | 32.31 | 54.83 | 64.13 | 16.90 | 39.40 | 63.25 | 70.50 | 15.89 | 18.21 | 37.96 | 57.88 | 15.98 | 34.45 | 57.90 | 68.10 | 25.25 | |
| ReCLIP [ 20 ] | 37.39 | 55.90 | 63.88 | 18.64 | 44.40 | 66.80 | 76.95 | 31.36 | 25.20 | 46.25 | 55.96 | 23.39 | 40.80 | 62.35 | 71.90 | 32.08 | |
| CFine [ 54 ] | 38.81 | 57.27 | 65.46 | - | 48.30 | 71.90 | 82.45 | - | 32.67 | 54.03 | 63.68 | 25.47 | 47.40 | 70.60 | 79.35 | 42.30 | |
| Methods | HGMA | SATA | ICFG-PEDES CUHK-PEDES | ICFG-PEDES RSTPReid | ||||||
| R@1 | R@5 | R@10 | mAP | R@1 | R@5 | R@10 | mAP | |||
| Baseline | 35.99 | 56.94 | 66.23 | 32.07 | 44.50 | 67.00 | 76.85 | 33.45 | ||
| + HGMA | 36.63 | 58.08 | 67.46 | 32.94 | 47.25 | 71.10 | 79.85 | 38.37 | ||
| + SATA | 41.03 | 59.71 | 67.46 | 36.11 | 50.15 | 72.10 | 80.90 | 37.32 | ||
| + STaG (Ours) | 44.23 | 65.09 | 73.08 | 38.64 | 53.70 | 75.00 | 82.60 | 40.15 | ||
| Methods | ICFG-PEDES CUHK-PEDES | ICFG-PEDES RSTPReid | |||||||||
| R@1 | R@5 | R@10 | mAP | R@1 | R@5 | R@10 | mAP | ||||
| Baseline | 36.63 | 58.08 | 67.46 | 32.94 | 47.25 | 71.10 | 79.85 | 38.37 | |||
| 38.50 | 60.00 | 68.47 | 33.24 | 48.30 | 72.20 | 79.95 | 38.40 | ||||
| 39.27 | 61.49 | 70.52 | 35.49 | 50.70 | 74.00 | 81.30 | 38.92 | ||||
| 40.39 | 62.23 | 71.09 | 36.22 | 51.30 | 74.55 | 82.00 | 39.11 | ||||
| (Ours) | 44.23 | 65.09 | 73.08 | 38.64 | 53.70 | 75.00 | 82.60 | 40.15 | |||
| Methods | ICFG-PEDES CUHK-PEDES | ICFG-PEDES RSTPReid | ||||||
| R@1 | R@5 | R@10 | mAP | R@1 | R@5 | R@10 | mAP | |
| Baseline | 41.03 | 59.71 | 67.46 | 36.11 | 50.15 | 72.10 | 80.90 | 37.32 |
| (STaG w/ ) | 41.57 | 60.29 | 67.88 | 36.40 | 50.65 | 72.50 | 81.00 | 37.56 |
| (STaG w/o ) | 43.72 | 64.89 | 72.85 | 38.29 | 51.55 | 73.45 | 81.70 | 38.83 |
| (STaG w/o ) | 42.88 | 63.90 | 71.91 | 37.56 | 51.05 | 72.85 | 80.55 | 37.81 |
| (STaG w/o ) | 43.44 | 64.42 | 72.87 | 38.56 | 51.60 | 74.40 | 81.20 | 38.43 |
Appendix figures & tables19 assets
Supplementary material from the paper’s appendix.
Appendix
| Symbol | Description | Reference |
| Source and target domain datasets | Sec. 3 | |
| -normalized image and text embeddings | Eq. 1 | |
| Symmetric image-text contrastive (InfoNCE) objective | Eq. 3 | |
| Generator-synthesized pseudo-descriptions | Sec. 3.2 | |
| Augmented datasets with generated pairs | Sec. 3.2 | |
| Style-Agnostic Text Alignment optimization objective | Sec. 3.2 |
| Generator Model | R@1 | R@5 | R@10 | mAP |
| InternVL2.5-8B (Default) | 44.23 | 65.09 | 73.08 | 38.64 |
| InternVL2-8B | 44.07 | 64.31 | 71.99 | 38.40 |
| Qwen2-VL-7B-Instruct | 43.84 | 64.11 | 71.15 | 37.94 |
| Noise Rate | R@1 | R@5 | R@10 | mAP |
| 0% (Original Pseudo-texts) | 44.23 | 65.09 | 73.08 | 38.64 |
| 10% | 43.87 | 64.55 | 72.63 | 38.28 |
| 20% | 44.05 | 64.88 | 72.99 | 38.49 |
| 30% | 43.13 | 62.85 | 71.23 | 37.67 |
| Corruption | Parameters | STaG | Baseline | ||
| R@1 | R@1 | ||||
| Original images | – | 44.23 | – | 35.99 | – |
| Mild corruption | |||||
| Gaussian blur | 44.39 | +0.16 | 35.77 | -0.22 | |
| Motion blur | 44.57 | +0.34 | 35.86 | -0.13 | |
| Low light + noise | 44.61 | +0.38 | 34.70 | -1.29 | |
| Metric | Baseline | Baseline + SATA (Ours) | Change |
| Centroid L2 Distance | 0.2821 | 0.1275 | |
| Pair Cosine Mean | 0.7883 | 0.8992 | |
| 37.80% | 51.35% | ||
| Method | R@1 | R@5 | R@10 | mAP |
| Baseline (HGMA Only) | 36.63 | 58.08 | 67.46 | 32.94 |
| + Random Noise Text | 38.50 | 60.00 | 68.47 | 33.24 |
| + 30% Hallucination | 43.13 | 62.85 | 71.23 | 37.67 |
| + SATA (Original) | 44.23 | 65.09 | 73.08 | 38.64 |
| Method | R@1 | R@5 | R@10 | mAP |
| Baseline (SATA Only) | 41.03 | 59.71 | 67.46 | 36.11 |
| + Random Neighbor | 41.57 | 60.29 | 67.88 | 36.40 |
| + HGMA (KNN-based) | 44.23 | 65.09 | 73.08 | 38.64 |
| Method | R@1 | R@5 | R@10 | mAP |
| Baseline | 35.99 | 56.94 | 66.23 | 32.07 |
| Plain pseudo-texts | 38.85 | 59.07 | 67.28 | 34.79 |
| STaG | 44.23 | 65.09 | 73.08 | 38.64 |
| CUHK-PEDES ICFG-PEDES | CUHK-PEDES RSTPReid | |||||||||
| Setting | Method | Ref. | R@1 | R@5 | R@10 | mAP | R@1 | R@5 | R@10 | mAP |
| Fully Supervised | IRRA [ 22 ] | CVPR’23 | 63.46 | 80.25 | 85.82 | 38.06 | 60.20 | 81.30 | 88.20 | 47.17 |
| RaSa [ 1 ] | IJCAI’23 | 65.28 | 80.40 | 85.12 | 41.29 | 66.90 | 86.50 | 91.35 | 52.31 | |
| TBPS-CLIP [ 5 ] | AAAI’24 | 65.05 | 80.34 | 85.47 | 39.83 | 61.60 | 81.20 | 87.70 | 47.71 | |
| RDE [ 42 ] | CVPR’24 | 67.68 | 82.47 | 87.36 | 40.06 | 65.35 | 83.95 | 89.90 | 50.88 | |
| PTMI [ 34 ] | TIFS’25 | 66.54 | 81.50 | 86.50 | 46.05 | 63.35 | 81.95 | 89.10 | 52.46 | |
| ICFG-PEDES CUHK-PEDES | ICFG-PEDES RSTPReid | |||||||||
| Setting | Method | Ref. | R@1 | R@5 | R@10 | mAP | R@1 | R@5 | R@10 | mAP |
| Fully Supervised | IRRA [ 22 ] | CVPR’23 | 73.38 | 89.93 | 93.71 | 66.13 | 60.20 | 81.30 | 88.20 | 47.17 |
| RaSa [ 1 ] | IJCAI’23 | 76.51 | 90.29 | 94.25 | 69.38 | 66.90 | 86.50 | 91.35 | 52.31 | |
| TBPS-CLIP [ 5 ] | AAAI’24 | 73.54 | 88.19 | 92.35 | 65.38 | 61.60 | 81.20 | 87.70 | 47.71 | |
| RDE [ 42 ] | CVPR’24 | 75.94 | 90.14 | 94.12 | 67.56 | 65.35 | 83.95 | 89.90 | 50.88 | |
| PTMI [ 34 ] | TIFS’25 | 76.02 | 89.93 | 94.14 | 70.85 | 63.35 | 81.95 | 89.10 | 52.46 | |
| RSTPReid CUHK-PEDES | RSTPReid ICFG-PEDES | |||||||||
| Setting | Method | Ref. | R@1 | R@5 | R@10 | mAP | R@1 | R@5 | R@10 | mAP |
| Fully Supervised | IRRA [ 22 ] | CVPR’23 | 73.38 | 89.93 | 93.71 | 66.13 | 63.46 | 80.25 | 85.82 | 38.06 |
| RaSa [ 1 ] | IJCAI’23 | 76.51 | 90.29 | 94.25 | 69.38 | 65.28 | 80.40 | 85.12 | 41.29 | |
| TBPS-CLIP [ 5 ] | AAAI’24 | 73.54 | 88.19 | 92.35 | 65.38 | 65.05 | 80.34 | 85.47 | 39.83 | |
| RDE [ 42 ] | CVPR’24 | 75.94 | 90.14 | 94.12 | 67.56 | 67.68 | 82.47 | 87.36 | 40.06 | |
| PTMI [ 34 ] | TIFS’25 | 76.02 | 89.93 | 94.14 | 70.85 | 66.54 | 81.50 | 86.50 | 46.05 | |
| Model | R@1 | R@5 | R@10 | mAP |
| Baseline | 44.50 | 67.00 | 76.85 | 33.45 |
| STaG w/o | 50.15 | 72.85 | 80.75 | 37.86 |
| STaG w/ | 50.55 | 73.50 | 81.45 | 37.92 |