Towards Fewer Labels: Support Pair Active Learning for Person Re-identification

• URL: http://arxiv.org/abs/2204.10008v1
• Date: Thu, 21 Apr 2022 10:10:18 GMT
• Title: Towards Fewer Labels: Support Pair Active Learning for Person Re-identification
• Authors: Dapeng Jin, Minxian Li
• Abstract summary: Supervised-learning based person re-identification (re-id) require a large amount of manual labeled data. We propose a Support Pair Active Learning framework to lower the manual labeling cost for large-scale person reidentification.
• Score: 5.076419064097734
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Supervised-learning based person re-identification (re-id) require a large amount of manual labeled data, which is not applicable in practical re-id deployment. In this work, we propose a Support Pair Active Learning (SPAL) framework to lower the manual labeling cost for large-scale person reidentification. The support pairs can provide the most informative relationships and support the discriminative feature learning. Specifically, we firstly design a dual uncertainty selection strategy to iteratively discover support pairs and require human annotations. Afterwards, we introduce a constrained clustering algorithm to propagate the relationships of labeled support pairs to other unlabeled samples. Moreover, a hybrid learning strategy consisting of an unsupervised contrastive loss and a supervised support pair loss is proposed to learn the discriminative re-id feature representation. The proposed overall framework can effectively lower the labeling cost by mining and leveraging the critical support pairs. Extensive experiments demonstrate the superiority of the proposed method over state-of-the-art active learning methods on large-scale person re-id benchmarks.

Related papers

• Class-aware and Augmentation-free Contrastive Learning from Label Proportion [19.41511190742059]
  Learning from Label Proportion (LLP) is a weakly supervised learning scenario in which training data is organized into predefined bags of instances. We propose an augmentation-free contrastive framework TabLLP-BDC that introduces class-aware supervision at the instance level. Our solution features a two-stage Bag Difference Contrastive (BDC) learning mechanism that establishes robust class-aware instance-level supervision.
  arXiv  Detail & Related papers  (2024-08-13T09:04:47Z)
• Robust Representation Learning for Unreliable Partial Label Learning [86.909511808373]
  Partial Label Learning (PLL) is a type of weakly supervised learning where each training instance is assigned a set of candidate labels, but only one label is the ground-truth. This is known as Unreliable Partial Label Learning (UPLL) that introduces an additional complexity due to the inherent unreliability and ambiguity of partial labels. We propose the Unreliability-Robust Representation Learning framework (URRL) that leverages unreliability-robust contrastive learning to help the model fortify against unreliable partial labels effectively.
  arXiv  Detail & Related papers  (2023-08-31T13:37:28Z)
• Prefer to Classify: Improving Text Classifiers via Auxiliary Preference Learning [76.43827771613127]
  In this paper, we investigate task-specific preferences between pairs of input texts as a new alternative way for such auxiliary data annotation. We propose a novel multi-task learning framework, called prefer-to-classify (P2C), which can enjoy the cooperative effect of learning both the given classification task and the auxiliary preferences.
  arXiv  Detail & Related papers  (2023-06-08T04:04:47Z)
• Leveraging Ensembles and Self-Supervised Learning for Fully-Unsupervised Person Re-Identification and Text Authorship Attribution [77.85461690214551]
  Learning from fully-unlabeled data is challenging in Multimedia Forensics problems, such as Person Re-Identification and Text Authorship Attribution. Recent self-supervised learning methods have shown to be effective when dealing with fully-unlabeled data in cases where the underlying classes have significant semantic differences. We propose a strategy to tackle Person Re-Identification and Text Authorship Attribution by enabling learning from unlabeled data even when samples from different classes are not prominently diverse.
  arXiv  Detail & Related papers  (2022-02-07T13:08:11Z)
• Feature Diversity Learning with Sample Dropout for Unsupervised Domain Adaptive Person Re-identification [0.0]
  This paper proposes a new approach to learn the feature representation with better generalization ability through limiting noisy pseudo labels. We put forward a brand-new method referred as to Feature Diversity Learning (FDL) under the classic mutual-teaching architecture. Experimental results show that our proposed FDL-SD achieves the state-of-the-art performance on multiple benchmark datasets.
  arXiv  Detail & Related papers  (2022-01-25T10:10:48Z)
• 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)
• Contrastive Learning for Fair Representations [50.95604482330149]
  Trained classification models can unintentionally lead to biased representations and predictions. Existing debiasing methods for classification models, such as adversarial training, are often expensive to train and difficult to optimise. We propose a method for mitigating bias by incorporating contrastive learning, in which instances sharing the same class label are encouraged to have similar representations.
  arXiv  Detail & Related papers  (2021-09-22T10:47:51Z)
• Dual-Refinement: Joint Label and Feature Refinement for Unsupervised Domain Adaptive Person Re-Identification [51.98150752331922]
  Unsupervised domain adaptive (UDA) person re-identification (re-ID) is a challenging task due to the missing of labels for the target domain data. We propose a novel approach, called Dual-Refinement, that jointly refines pseudo labels at the off-line clustering phase and features at the on-line training phase. Our method outperforms the state-of-the-art methods by a large margin.
  arXiv  Detail & Related papers  (2020-12-26T07:35:35Z)
• Unsupervised Attention Based Instance Discriminative Learning for Person Re-Identification [5.233788055084763]
  We propose an unsupervised framework for person re-identification which is trained in an end-to-end manner without pre-training. Our proposed framework leverages a new attention mechanism that combines group convolutions to enhance spatial attention at multiple scales. We perform extensive analysis using the Market1501 and DukeMTMC-reID datasets to demonstrate that our method consistently outperforms the state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-11-03T18:08:31Z)
• Heuristic-Based Weak Learning for Automated Decision-Making [0.0]
  Machine learning systems impact many stakeholders and groups of users, often disparately. Prior studies have reconciled conflicting user preferences by aggregating a high volume of manually labeled pairwise comparisons. We show that our weak learning approach, which requires little to no manual labeling, agrees with participants' pairwise choices nearly as often as fully supervised approaches.
  arXiv  Detail & Related papers  (2020-05-05T17:22:52Z)
• Learning What Makes a Difference from Counterfactual Examples and Gradient Supervision [57.14468881854616]
  We propose an auxiliary training objective that improves the generalization capabilities of neural networks. We use pairs of minimally-different examples with different labels, a.k.a counterfactual or contrasting examples, which provide a signal indicative of the underlying causal structure of the task. Models trained with this technique demonstrate improved performance on out-of-distribution test sets.
  arXiv  Detail & Related papers  (2020-04-20T02:47:49Z)

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.