Take More Positives: An Empirical Study of Contrastive Learing in Unsupervised Person Re-Identification

• URL: http://arxiv.org/abs/2101.04340v2
• Date: Fri, 19 Mar 2021 06:23:34 GMT
• Title: Take More Positives: An Empirical Study of Contrastive Learing in Unsupervised Person Re-Identification
• Authors: Xuanyu He, Wei Zhang, Ran Song, Qian Zhang, Xiangyuan Lan, Lin Ma
• Abstract summary: Unsupervised person re-ID aims at closing the performance gap to supervised methods. We show that the reason why they are successful is not only their label generation mechanisms, but also their unexplored designs. We propose a contrastive learning method without a memory back for unsupervised person re-ID.
• Score: 43.11532800327356
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Unsupervised person re-identification (re-ID) aims at closing the performance gap to supervised methods. These methods build reliable relationship between data points while learning representations. However, we empirically show that the reason why they are successful is not only their label generation mechanisms, but also their unexplored designs. By studying two unsupervised person re-ID methods in a cross-method way, we point out a hard negative problem is handled implicitly by their designs of data augmentations and PK sampler respectively. In this paper, we find another simple solution for the problem, i.e., taking more positives during training, by which we generate pseudo-labels and update models in an iterative manner. Based on our findings, we propose a contrastive learning method without a memory back for unsupervised person re-ID. Our method works well on benchmark datasets and outperforms the state-of-the-art methods. Code will be made available.

Related papers

• Segue: Side-information Guided Generative Unlearnable Examples for Facial Privacy Protection in Real World [64.4289385463226]
  We propose Segue: Side-information guided generative unlearnable examples. To improve transferability, we introduce side information such as true labels and pseudo labels. It can resist JPEG compression, adversarial training, and some standard data augmentations.
  arXiv  Detail & Related papers  (2023-10-24T06:22:37Z)
• Unsupervised Few-shot Learning via Deep Laplacian Eigenmaps [13.6555672824229]
  We present an unsupervised few-shot learning method via deep Laplacian eigenmaps. Our method learns representation from unlabeled data by grouping similar samples together. We analytically show how deep Laplacian eigenmaps avoid collapsed representation in unsupervised learning.
  arXiv  Detail & Related papers  (2022-10-07T14:53:03Z)
• Non-contrastive representation learning for intervals from well logs [58.70164460091879]
  The representation learning problem in the oil & gas industry aims to construct a model that provides a representation based on logging data for a well interval. One of the possible approaches is self-supervised learning (SSL) We are the first to introduce non-contrastive SSL for well-logging data.
  arXiv  Detail & Related papers  (2022-09-28T13:27:10Z)
• Unsupervised Clustering Active Learning for Person Re-identification [5.705895028045853]
  Unsupervised re-id methods rely on unlabeled data to train models. We present a Unsupervised Clustering Active Learning (UCAL) re-id deep learning approach. It is capable of incrementally discovering the representative centroid-pairs.
  arXiv  Detail & Related papers  (2021-12-26T02:54:35Z)
• Hard-sample Guided Hybrid Contrast Learning for Unsupervised Person Re-Identification [8.379286663107845]
  Unsupervised person re-identification (Re-ID) is a promising and very challenging research problem in computer vision. We propose a Hard-sample Guided Hybrid Contrast Learning (HHCL) approach combining cluster-level loss with instance-level loss for unsupervised person Re-ID. Experiments on two popular large-scale Re-ID benchmarks demonstrate that our HHCL outperforms previous state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-09-25T10:43:37Z)
• Hard Samples Rectification for Unsupervised Cross-domain Person Re-identification [29.293741858274146]
  We propose a Hard Samples Rectification learning scheme which resolves the weakness of original clustering-based methods. Our HSR contains two parts, an inter-camera mining method that helps recognize a person under different views (hard positive) and a part-based homogeneity technique that makes the model discriminate different persons but with similar appearance (hard negative) By rectifying those two hard cases, the re-ID model can learn effectively and achieve promising results on two large-scale benchmarks.
  arXiv  Detail & Related papers  (2021-06-14T07:38:42Z)
• Unsupervised Noisy Tracklet Person Re-identification [100.85530419892333]
  We present a novel selective tracklet learning (STL) approach that can train discriminative person re-id models from unlabelled tracklet data. This avoids the tedious and costly process of exhaustively labelling person image/tracklet true matching pairs across camera views. Our method is particularly more robust against arbitrary noisy data of raw tracklets therefore scalable to learning discriminative models from unconstrained tracking data.
  arXiv  Detail & Related papers  (2021-01-16T07:31:00Z)
• A Sober Look at the Unsupervised Learning of Disentangled Representations and their Evaluation [63.042651834453544]
  We show that the unsupervised learning of disentangled representations is impossible without inductive biases on both the models and the data. We observe that while the different methods successfully enforce properties "encouraged" by the corresponding losses, well-disentangled models seemingly cannot be identified without supervision. Our results suggest that future work on disentanglement learning should be explicit about the role of inductive biases and (implicit) supervision.
  arXiv  Detail & Related papers  (2020-10-27T10:17:15Z)
• CycAs: Self-supervised Cycle Association for Learning Re-identifiable Descriptions [61.724894233252414]
  This paper proposes a self-supervised learning method for the person re-identification (re-ID) problem. Existing unsupervised methods usually rely on pseudo labels, such as those from video tracklets or clustering. We introduce a different unsupervised method that allows us to learn pedestrian embeddings from raw videos, without resorting to pseudo labels.
  arXiv  Detail & Related papers  (2020-07-15T09:52:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.