SSKD: Self-Supervised Knowledge Distillation for Cross Domain Adaptive Person Re-Identification

• URL: http://arxiv.org/abs/2009.05972v1
• Date: Sun, 13 Sep 2020 10:12:02 GMT
• Title: SSKD: Self-Supervised Knowledge Distillation for Cross Domain Adaptive Person Re-Identification
• Authors: Junhui Yin, Jiayan Qiu, Siqing Zhang, Zhanyu Ma, Jun Guo
• Abstract summary: Domain adaptive person re-identification (re-ID) is a challenging task due to the large discrepancy between the source domain and the target domain. Existing methods mainly attempt to generate pseudo labels for unlabeled target images by clustering algorithms. We propose a Self-Supervised Knowledge Distillation (SSKD) technique containing two modules, the identity learning and the soft label learning.
• Score: 25.96221714337815
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Domain adaptive person re-identification (re-ID) is a challenging task due to the large discrepancy between the source domain and the target domain. To reduce the domain discrepancy, existing methods mainly attempt to generate pseudo labels for unlabeled target images by clustering algorithms. However, clustering methods tend to bring noisy labels and the rich fine-grained details in unlabeled images are not sufficiently exploited. In this paper, we seek to improve the quality of labels by capturing feature representation from multiple augmented views of unlabeled images. To this end, we propose a Self-Supervised Knowledge Distillation (SSKD) technique containing two modules, the identity learning and the soft label learning. Identity learning explores the relationship between unlabeled samples and predicts their one-hot labels by clustering to give exact information for confidently distinguished images. Soft label learning regards labels as a distribution and induces an image to be associated with several related classes for training peer network in a self-supervised manner, where the slowly evolving network is a core to obtain soft labels as a gentle constraint for reliable images. Finally, the two modules can resist label noise for re-ID by enhancing each other and systematically integrating label information from unlabeled images. Extensive experiments on several adaptation tasks demonstrate that the proposed method outperforms the current state-of-the-art approaches by large margins.

Related papers

• Few-shot Class-Incremental Semantic Segmentation via Pseudo-Labeling and Knowledge Distillation [3.4436201325139737]
  We address the problem of learning new classes for semantic segmentation models from few examples. For learning from limited data, we propose a pseudo-labeling strategy to augment the few-shot training annotations. We integrate the above steps into a single convolutional neural network with a unified learning objective.
  arXiv  Detail & Related papers  (2023-08-05T05:05:37Z)
• Semantic-Aware Graph Matching Mechanism for Multi-Label Image Recognition [21.36538164675385]
  Multi-label image recognition aims to predict a set of labels that present in an image. In this paper, we treat each image as a bag of instances, and formulate the task of multi-label image recognition as an instance-label matching selection problem. We propose an innovative Semantic-aware Graph Matching framework for Multi-Label image recognition (ML-SGM)
  arXiv  Detail & Related papers  (2023-04-21T23:48:01Z)
• Towards Effective Multi-Label Recognition Attacks via Knowledge Graph Consistency [33.250544869840155]
  We show that the naive extensions of multi-class attacks to the multi-label setting lead to violating label relationships. We propose a graph-consistent multi-label attack framework, which searches for small image perturbations that lead to misclassifying a desired target set.
  arXiv  Detail & Related papers  (2022-07-11T19:08:32Z)
• Dual-Perspective Semantic-Aware Representation Blending for Multi-Label Image Recognition with Partial Labels [70.36722026729859]
  We propose a dual-perspective semantic-aware representation blending (DSRB) that blends multi-granularity category-specific semantic representation across different images. The proposed DS consistently outperforms current state-of-the-art algorithms on all proportion label settings.
  arXiv  Detail & Related papers  (2022-05-26T00:33:44Z)
• Heterogeneous Semantic Transfer for Multi-label Recognition with Partial Labels [70.45813147115126]
  Multi-label image recognition with partial labels (MLR-PL) may greatly reduce the cost of annotation and thus facilitate large-scale MLR. We find that strong semantic correlations exist within each image and across different images. These correlations can help transfer the knowledge possessed by the known labels to retrieve the unknown labels.
  arXiv  Detail & Related papers  (2022-05-23T08:37:38Z)
• Structured Semantic Transfer for Multi-Label Recognition with Partial Labels [85.6967666661044]
  We propose a structured semantic transfer (SST) framework that enables training multi-label recognition models with partial labels. The framework consists of two complementary transfer modules that explore within-image and cross-image semantic correlations. Experiments on the Microsoft COCO, Visual Genome and Pascal VOC datasets show that the proposed SST framework obtains superior performance over current state-of-the-art algorithms.
  arXiv  Detail & Related papers  (2021-12-21T02:15:01Z)
• Simpler Does It: Generating Semantic Labels with Objectness Guidance [32.81128493853064]
  We present a novel framework that generates pseudo-labels for training images, which are then used to train a segmentation model. To generate pseudo-labels, we combine information from: (i) a class agnostic objectness network that learns to recognize object-like regions, and (ii) either image-level or bounding box annotations. We show the efficacy of our approach by demonstrating how the objectness network can naturally be leveraged to generate object-like regions for unseen categories.
  arXiv  Detail & Related papers  (2021-10-20T01:52:05Z)
• 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)
• Semantics-Guided Clustering with Deep Progressive Learning for Semi-Supervised Person Re-identification [58.01834972099855]
  Person re-identification (re-ID) requires one to match images of the same person across camera views. We propose a novel framework of Semantics-Guided Clustering with Deep Progressive Learning (SGC-DPL) to jointly exploit the above data. Our approach is able to augment the labeled training data in the semi-supervised setting.
  arXiv  Detail & Related papers  (2020-10-02T18:02:35Z)
• Knowledge-Guided Multi-Label Few-Shot Learning for General Image Recognition [75.44233392355711]
  KGGR framework exploits prior knowledge of statistical label correlations with deep neural networks. It first builds a structured knowledge graph to correlate different labels based on statistical label co-occurrence. Then, it introduces the label semantics to guide learning semantic-specific features. It exploits a graph propagation network to explore graph node interactions.
  arXiv  Detail & Related papers  (2020-09-20T15:05:29Z)

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.