# CycAs: Self-supervised Cycle Association for Learning Re-identifiable Descriptions

arXiv: https://arxiv.org/abs/2007.07577 · HTML: https://mlsanity.com/paper/2007.07577/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jul 2020.

## Built on by (most cited first, 30 of 36)

- [A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trends](https://mlsanity.com/paper/2301.05712/) (2023)
- [Cluster Contrast for Unsupervised Person Re-Identification](https://mlsanity.com/paper/2103.11568/) (2021)
- [ICE: Inter-instance Contrastive Encoding for Unsupervised Person Re-identification](https://mlsanity.com/paper/2103.16364/) (2021)
- [Implicit Sample Extension for Unsupervised Person Re-Identification](https://mlsanity.com/paper/2204.06892/) (2022)
- [Hybrid Dynamic Contrast and Probability Distillation for Unsupervised Person Re-Id](https://mlsanity.com/paper/2109.14157/) (2021)
- [Online Multi-Object Tracking with Unsupervised Re-Identification Learning and Occlusion Estimation](https://mlsanity.com/paper/2201.01297/) (2022)
- [MSINet: Twins Contrastive Search of Multi-Scale Interaction for Object ReID](https://mlsanity.com/paper/2303.07065/) (2023)
- [Identity-Seeking Self-Supervised Representation Learning for Generalizable Person Re-identification](https://mlsanity.com/paper/2308.08887/) (2023)
- [Hard-sample Guided Hybrid Contrast Learning for Unsupervised Person Re-Identification](https://mlsanity.com/paper/2109.12333/) (2021)
- [Uncertainty-aware Unsupervised Multi-Object Tracking](https://mlsanity.com/paper/2307.15409/) (2023)
- [Learning to Purification for Unsupervised Person Re-identification](https://mlsanity.com/paper/2204.09931/) (2022)
- [MGH: Metadata Guided Hypergraph Modeling for Unsupervised Person Re-identification](https://mlsanity.com/paper/2110.05886/) (2021)
- [Offline-Online Associated Camera-Aware Proxies for Unsupervised Person Re-identification](https://mlsanity.com/paper/2201.05820/) (2022)
- [Tracking without Label: Unsupervised Multiple Object Tracking via Contrastive Similarity Learning](https://mlsanity.com/paper/2309.00942/) (2023)
- [Unsupervised Person Re-identification with Stochastic Training Strategy](https://mlsanity.com/paper/2108.06938/) (2021)
- [Self-Supervised Multi-Object Tracking For Autonomous Driving From Consistency Across Timescales](https://mlsanity.com/paper/2304.13147/) (2023)
- [Learning from Synchronization: Self-Supervised Uncalibrated Multi-View Person Association in Challenging Scenes](https://mlsanity.com/paper/2503.13739/) (2025)
- [Unsupervised and self-adaptative techniques for cross-domain person re-identification](https://mlsanity.com/paper/2103.11520/) (2021)
- [Rethinking Sampling Strategies for Unsupervised Person Re-identification](https://mlsanity.com/paper/2107.03024/) (2021)
- [Meta Clustering Learning for Large-scale Unsupervised Person Re-identification](https://mlsanity.com/paper/2111.10032/) (2021)
- [Population-Based Evolutionary Gaming for Unsupervised Person Re-identification](https://mlsanity.com/paper/2306.05236/) (2023)
- [Large-Scale Unsupervised Person Re-Identification with Contrastive Learning](https://mlsanity.com/paper/2105.07914/) (2021)
- [Temporal Transformer Networks with Self-Supervision for Action Recognition](https://mlsanity.com/paper/2112.07338/) (2021)
- [Camera-aware Style Separation and Contrastive Learning for Unsupervised Person Re-identification](https://mlsanity.com/paper/2112.10089/) (2021)
- [Leveraging Ensembles and Self-Supervised Learning for Fully-Unsupervised Person Re-Identification and Text Authorship Attribution](https://mlsanity.com/paper/2202.03126/) (2022)
- [Spatial Cascaded Clustering and Weighted Memory for Unsupervised Person Re-identification](https://mlsanity.com/paper/2403.00261/) (2024)
- [Unsupervised Person Re-identification via Simultaneous Clustering and Consistency Learning](https://mlsanity.com/paper/2104.00202/) (2021)
- [Neighbour Consistency Guided Pseudo-Label Refinement for Unsupervised Person Re-Identification](https://mlsanity.com/paper/2211.16847/) (2022)
- [Large-scale Fully-Unsupervised Re-Identification](https://mlsanity.com/paper/2307.14278/) (2023)
- [Adaptive Intra-Class Variation Contrastive Learning for Unsupervised Person Re-Identification](https://mlsanity.com/paper/2404.04665/) (2024)

## Abstract (arXiv)

This paper proposes a self-supervised learning method for the person re-identification (re-ID) problem, where existing unsupervised methods usually rely on pseudo labels, such as those from video tracklets or clustering. A potential drawback of using pseudo labels is that errors may accumulate and it is challenging to estimate the number of pseudo IDs. We introduce a different unsupervised method that allows us to learn pedestrian embeddings from raw videos, without resorting to pseudo labels. The goal is to construct a self-supervised pretext task that matches the person re-ID objective. Inspired by the data association concept in multi-object tracking, we propose the Cycle Association (CycAs) task: after performing data association between a pair of video frames forward and then backward, a pedestrian instance is supposed to be associated to itself. To fulfill this goal, the model must learn a meaningful representation that can well describe correspondences between instances in frame pairs. We adapt the discrete association process to a differentiable form, such that end-to-end training becomes feasible. Experiments are conducted in two aspects: We first compare our method with existing unsupervised re-ID methods on seven benchmarks and demonstrate CycAs' superiority. Then, to further validate the practical value of CycAs in real-world applications, we perform training on self-collected videos and report promising performance on standard test sets.