# Try Harder: Hard Sample Generation and Learning for Clothes-Changing Person Re-ID

arXiv: https://arxiv.org/abs/2507.11119 · HTML: https://mlsanity.com/paper/2507.11119/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 65 references that are in the map.
- First posted on arXiv 15 Jul 2025.

## Builds on (most cited first, 30 of 38)

- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Palette: Image-to-Image Diffusion Models](https://mlsanity.com/paper/2111.05826/) (2021)
- [Diffusion Models in Vision: A Survey](https://mlsanity.com/paper/2209.04747/) (2022)
- [In Defense of the Triplet Loss for Person Re-Identification](https://mlsanity.com/paper/1703.07737/) (2017)
- [VideoBERT: A Joint Model for Video and Language Representation Learning](https://mlsanity.com/paper/1904.01766/) (2019)
- [AudioLM: a Language Modeling Approach to Audio Generation](https://mlsanity.com/paper/2209.03143/) (2022)
- [Deep Learning for Person Re-identification: A Survey and Outlook](https://mlsanity.com/paper/2001.04193/) (2020)
- [TransReID: Transformer-based Object Re-Identification](https://mlsanity.com/paper/2102.04378/) (2021)
- [VITON-HD: High-Resolution Virtual Try-On via Misalignment-Aware Normalization](https://mlsanity.com/paper/2103.16874/) (2021)
- [VITON: An Image-based Virtual Try-on Network](https://mlsanity.com/paper/1711.08447/) (2017)
- [Self-Correction for Human Parsing](https://mlsanity.com/paper/1910.09777/) (2019)
- [StableVITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-On](https://mlsanity.com/paper/2312.01725/) (2023)
- [Taming the Power of Diffusion Models for High-Quality Virtual Try-On with Appearance Flow](https://mlsanity.com/paper/2308.06101/) (2023)
- [Improving Diffusion Models for Authentic Virtual Try-on in the Wild](https://mlsanity.com/paper/2403.05139/) (2024)
- [Clothes-Changing Person Re-identification with RGB Modality Only](https://mlsanity.com/paper/2204.06890/) (2022)
- [Person Re-identification by Contour Sketch under Moderate Clothing Change](https://mlsanity.com/paper/2002.02295/) (2020)
- [Long-Term Cloth-Changing Person Re-identification](https://mlsanity.com/paper/2005.12633/) (2020)
- [Cloth-Changing Person Re-identification from A Single Image with Gait Prediction and Regularization](https://mlsanity.com/paper/2103.15537/) (2021)
- [Camera Style Adaptation for Person Re-identification](https://mlsanity.com/paper/1711.10295/) (2017)
- [Unsupervised Person Re-identification by Soft Multilabel Learning](https://mlsanity.com/paper/1903.06325/) (2019)
- [CAT-DM: Controllable Accelerated Virtual Try-on with Diffusion Model](https://mlsanity.com/paper/2311.18405/) (2023)
- [Texture-Preserving Diffusion Models for High-Fidelity Virtual Try-On](https://mlsanity.com/paper/2404.01089/) (2024)
- [UnrealPerson: An Adaptive Pipeline towards Costless Person Re-identification](https://mlsanity.com/paper/2012.04268/) (2020)
- [From Poses to Identity: Training-Free Person Re-Identification via Feature Centralization](https://mlsanity.com/paper/2503.00938/) (2025)
- [TryOffAnyone: Tiled Cloth Generation from a Dressed Person](https://mlsanity.com/paper/2412.08573/) (2024)
- [Multigranular Visual-Semantic Embedding for Cloth-Changing Person Re-identification](https://mlsanity.com/paper/2108.04527/) (2021)
- [DIFFER: Disentangling Identity Features via Semantic Cues for Clothes-Changing Person Re-ID](https://mlsanity.com/paper/2503.22912/) (2025)
- [DLCR: A Generative Data Expansion Framework via Diffusion for Clothes-Changing Person Re-ID](https://mlsanity.com/paper/2411.07205/) (2024)

## Built on by (most cited first, 5 of 5)

- [Modality-Transition Representation Learning for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2511.02685/) (2025)
- [MOS: Mitigating Optical-SAR Modality Gap for Cross-Modal Ship Re-Identification](https://mlsanity.com/paper/2512.03404/) (2025)
- [BIT: Matching-based Bi-directional Interaction Transformation Network for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2603.14243/) (2026)
- [Towards Robust Text-to-Image Person Retrieval: Multi-View Reformulation for Semantic Compensation](https://mlsanity.com/paper/2604.18376/) (2026)
- [Dual-Space Modality Consistency Learning for Universal Cross-Modal Re-Identification](https://mlsanity.com/paper/2608.06943/) (2026)

## Abstract (arXiv)

Hard samples pose a significant challenge in person re-identification (ReID) tasks, particularly in clothing-changing person Re-ID (CC-ReID). Their inherent ambiguity or similarity, coupled with the lack of explicit definitions, makes them a fundamental bottleneck. These issues not only limit the design of targeted learning strategies but also diminish the model's robustness under clothing or viewpoint changes. In this paper, we propose a novel multimodal-guided Hard Sample Generation and Learning (HSGL) framework, which is the first effort to unify textual and visual modalities to explicitly define, generate, and optimize hard samples within a unified paradigm. HSGL comprises two core components: (1) Dual-Granularity Hard Sample Generation (DGHSG), which leverages multimodal cues to synthesize semantically consistent samples, including both coarse- and fine-grained hard positives and negatives for effectively increasing the hardness and diversity of the training data. (2) Hard Sample Adaptive Learning (HSAL), which introduces a hardness-aware optimization strategy that adjusts feature distances based on textual semantic labels, encouraging the separation of hard positives and drawing hard negatives closer in the embedding space to enhance the model's discriminative capability and robustness to hard samples. Extensive experiments on multiple CC-ReID benchmarks demonstrate the effectiveness of our approach and highlight the potential of multimodal-guided hard sample generation and learning for robust CC-ReID. Notably, HSAL significantly accelerates the convergence of the targeted learning procedure and achieves state-of-the-art performance on both PRCC and LTCC datasets. The code is available at https://github.com/undooo/TryHarder-ACMMM25.