# CLIP-DFGS: A Hard Sample Mining Method for CLIP in Generalizable Person Re-Identification

arXiv: https://arxiv.org/abs/2410.11255 · HTML: https://mlsanity.com/paper/2410.11255/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 60 references that are in the map.
- First posted on arXiv 15 Oct 2024.

## Builds on (most cited first, 30 of 31)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [In Defense of the Triplet Loss for Person Re-Identification](https://mlsanity.com/paper/1703.07737/) (2017)
- [Deep Learning for Person Re-identification: A Survey and Outlook](https://mlsanity.com/paper/2001.04193/) (2020)
- [Person Transfer GAN to Bridge Domain Gap for Person Re-Identification](https://mlsanity.com/paper/1711.08565/) (2017)
- [TransReID: Transformer-based Object Re-Identification](https://mlsanity.com/paper/2102.04378/) (2021)
- [Person Re-identification: Past, Present and Future](https://mlsanity.com/paper/1610.02984/) (2016)
- [CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels](https://mlsanity.com/paper/2211.13977/) (2022)
- [A Strong Baseline and Batch Normalization Neck for Deep Person Re-identification](https://mlsanity.com/paper/1906.08332/) (2019)
- [Person Search with Natural Language Description](https://mlsanity.com/paper/1702.05729/) (2017)
- [Style Normalization and Restitution for Generalizable Person Re-identification](https://mlsanity.com/paper/2005.11037/) (2020)
- [Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval](https://mlsanity.com/paper/2303.12501/) (2023)
- [Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identification](https://mlsanity.com/paper/2012.00417/) (2020)
- [Semantically Self-Aligned Network for Text-to-Image Part-aware Person Re-identification](https://mlsanity.com/paper/2107.12666/) (2021)
- [DSSL: Deep Surroundings-person Separation Learning for Text-based Person Retrieval](https://mlsanity.com/paper/2109.05534/) (2021)
- [Meta Batch-Instance Normalization for Generalizable Person Re-Identification](https://mlsanity.com/paper/2011.14670/) (2020)
- [Generalizable Person Re-identification with Relevance-aware Mixture of Experts](https://mlsanity.com/paper/2105.09156/) (2021)
- [Frustratingly Easy Person Re-Identification: Generalizing Person Re-ID in Practice](https://mlsanity.com/paper/1905.03422/) (2019)
- [Learning Disentangled Representation for Robust Person Re-identification](https://mlsanity.com/paper/1910.12003/) (2019)
- [CAIBC: Capturing All-round Information Beyond Color for Text-based Person Retrieval](https://mlsanity.com/paper/2209.05773/) (2022)
- [Beyond Triplet Loss: Person Re-identification with Fine-grained Difference-aware Pairwise Loss](https://mlsanity.com/paper/2009.10295/) (2020)
- [TransMatcher: Deep Image Matching Through Transformers for Generalizable Person Re-identification](https://mlsanity.com/paper/2105.14432/) (2021)
- [Improving Deep Visual Representation for Person Re-identification by Global and Local Image-language Association](https://mlsanity.com/paper/1808.01571/) (2018)
- [Dual Distribution Alignment Network for Generalizable Person Re-Identification](https://mlsanity.com/paper/2007.13249/) (2020)
- [Calibrated Domain-Invariant Learning for Highly Generalizable Large Scale Re-Identification](https://mlsanity.com/paper/1911.11314/) (2019)
- [One for More: Selecting Generalizable Samples for Generalizable ReID Model](https://mlsanity.com/paper/2012.05475/) (2020)
- [Semi-Supervised Domain Generalizable Person Re-Identification](https://mlsanity.com/paper/2108.05045/) (2021)
- [A Convolutional Baseline for Person Re-Identification Using Vision and Language Descriptions](https://mlsanity.com/paper/2003.00808/) (2020)
- [Domain Generalized Person Re-Identification via Cross-Domain Episodic Learning](https://mlsanity.com/paper/2010.09561/) (2020)

## Built on by (most cited first, 7 of 7)

- [Try Harder: Hard Sample Generation and Learning for Clothes-Changing Person Re-ID](https://mlsanity.com/paper/2507.11119/) (2025)
- [Domain Generalization for Person Re-identification: A Survey Towards Domain-Agnostic Person Matching](https://mlsanity.com/paper/2506.12413/) (2025)
- [DynaMix: Generalizable Person Re-identification via Dynamic Relabeling and Mixed Data Sampling](https://mlsanity.com/paper/2511.19067/) (2025)
- [VReID-XFD: Video-based Person Re-identification at Extreme Far Distance Challenge Results](https://mlsanity.com/paper/2601.01312/) (2026)
- [ReText: Text Boosts Generalization in Image-Based Person Re-identification](https://mlsanity.com/paper/2602.05785/) (2026)
- [Multimodal LLM-Empowered Re-Ranking for Generalizable Person Re-Identification](https://mlsanity.com/paper/2606.16161/) (2026)
- [Cross-Species Animal Re-Identification with Semantic Consistency Learning](https://mlsanity.com/paper/2609.09705/) (2026)

## Abstract (arXiv)

Recent advancements in pre-trained vision-language models like CLIP have shown promise in person re-identification (ReID) applications. However, their performance in generalizable person re-identification tasks remains suboptimal. The large-scale and diverse image-text pairs used in CLIP's pre-training may lead to a lack or insufficiency of certain fine-grained features. In light of these challenges, we propose a hard sample mining method called DFGS (Depth-First Graph Sampler), based on depth-first search, designed to offer sufficiently challenging samples to enhance CLIP's ability to extract fine-grained features. DFGS can be applied to both the image encoder and the text encoder in CLIP. By leveraging the powerful cross-modal learning capabilities of CLIP, we aim to apply our DFGS method to extract challenging samples and form mini-batches with high discriminative difficulty, providing the image model with more efficient and challenging samples that are difficult to distinguish, thereby enhancing the model's ability to differentiate between individuals. Our results demonstrate significant improvements over other methods, confirming the effectiveness of DFGS in providing challenging samples that enhance CLIP's performance in generalizable person re-identification.