# Contrastive Multiple Instance Learning for Weakly Supervised Person ReID

arXiv: https://arxiv.org/abs/2402.07685 · HTML: https://mlsanity.com/paper/2402.07685/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 51 references that are in the map.
- First posted on arXiv 12 Feb 2024.

## Builds on (most cited first, 30 of 32)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [In Defense of the Triplet Loss for Person Re-Identification](https://mlsanity.com/paper/1703.07737/) (2017)
- [Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization](https://mlsanity.com/paper/1603.06560/) (2016)
- [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)
- [Learning Discriminative Features with Multiple Granularities for Person Re-Identification](https://mlsanity.com/paper/1804.01438/) (2018)
- [Harmonious Attention Network for Person Re-Identification](https://mlsanity.com/paper/1802.08122/) (2018)
- [Joint Detection and Identification Feature Learning for Person Search](https://mlsanity.com/paper/1604.01850/) (2016)
- [Person Re-identification: Past, Present and Future](https://mlsanity.com/paper/1610.02984/) (2016)
- [Person Re-identification in the Wild](https://mlsanity.com/paper/1604.02531/) (2016)
- [Unsupervised Person Re-identification via Multi-label Classification](https://mlsanity.com/paper/2004.09228/) (2020)
- [Unsupervised Pre-training for Person Re-identification](https://mlsanity.com/paper/2012.03753/) (2020)
- [Weakly Supervised Contrastive Learning](https://mlsanity.com/paper/2110.04770/) (2021)
- [Unsupervised Person Re-identification via Softened Similarity Learning](https://mlsanity.com/paper/2004.03547/) (2020)
- [Unsupervised Person Re-identification: Clustering and Fine-tuning](https://mlsanity.com/paper/1705.10444/) (2017)
- [C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection](https://mlsanity.com/paper/1904.05647/) (2019)
- [Unsupervised Person Re-identification by Soft Multilabel Learning](https://mlsanity.com/paper/1903.06325/) (2019)
- [Beyond Human Parts: Dual Part-Aligned Representations for Person Re-Identification](https://mlsanity.com/paper/1910.10111/) (2019)
- [Unsupervised Person Re-identification by Deep Learning Tracklet Association](https://mlsanity.com/paper/1809.02874/) (2018)
- [Solving Inefficiency of Self-supervised Representation Learning](https://mlsanity.com/paper/2104.08760/) (2021)
- [Large-Scale Pre-training for Person Re-identification with Noisy Labels](https://mlsanity.com/paper/2203.16533/) (2022)
- [Self-Supervised Pre-Training for Transformer-Based Person Re-Identification](https://mlsanity.com/paper/2111.12084/) (2021)
- [A Siamese Long Short-Term Memory Architecture for Human Re-Identification](https://mlsanity.com/paper/1607.08381/) (2016)
- [Deep Feature Learning with Relative Distance Comparison for Person Re-identification](https://mlsanity.com/paper/1512.03622/) (2015)
- [Learning Person Re-identification Models from Videos with Weak Supervision](https://mlsanity.com/paper/2007.10631/) (2020)
- [DARI: Distance metric And Representation Integration for Person Verification](https://mlsanity.com/paper/1604.04377/) (2016)
- [Weakly Supervised Person Re-Identification](https://mlsanity.com/paper/1904.03832/) (2019)

## Abstract (arXiv)

The acquisition of large-scale, precisely labeled datasets for person re-identification (ReID) poses a significant challenge. Weakly supervised ReID has begun to address this issue, although its performance lags behind fully supervised methods. In response, we introduce Contrastive Multiple Instance Learning (CMIL), a novel framework tailored for more effective weakly supervised ReID. CMIL distinguishes itself by requiring only a single model and no pseudo labels while leveraging contrastive losses -- a technique that has significantly enhanced traditional ReID performance yet is absent in all prior MIL-based approaches. Through extensive experiments and analysis across three datasets, CMIL not only matches state-of-the-art performance on the large-scale SYSU-30k dataset with fewer assumptions but also consistently outperforms all baselines on the WL-market1501 and Weakly Labeled MUddy racer re-iDentification dataset (WL-MUDD) datasets. We introduce and release the WL-MUDD dataset, an extension of the MUDD dataset featuring naturally occurring weak labels from the real-world application at PerformancePhoto.co. All our code and data are accessible at https://drive.google.com/file/d/1rjMbWB6m-apHF3Wg_cfqc8QqKgQ21AsT/view?usp=drive_link.