Weakly Supervised Person Search with Region Siamese Networks

• URL: http://arxiv.org/abs/2109.06109v1
• Date: Mon, 13 Sep 2021 16:33:27 GMT
• Title: Weakly Supervised Person Search with Region Siamese Networks
• Authors: Chuchu Han, Kai Su, Dongdong Yu, Zehuan Yuan, Changxin Gao, Nong Sang, Yi Yang and Changhu Wang
• Abstract summary: Supervised learning is dominant in person search, but it requires elaborate labeling of bounding boxes and identities. We present a weakly supervised setting where only bounding box annotations are available. Our model achieves the rank-1 of 87.1% and mAP of 86.0% on CUHK-SYSU benchmark.
• Score: 65.76237418040071
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Supervised learning is dominant in person search, but it requires elaborate labeling of bounding boxes and identities. Large-scale labeled training data is often difficult to collect, especially for person identities. A natural question is whether a good person search model can be trained without the need of identity supervision. In this paper, we present a weakly supervised setting where only bounding box annotations are available. Based on this new setting, we provide an effective baseline model termed Region Siamese Networks (R-SiamNets). Towards learning useful representations for recognition in the absence of identity labels, we supervise the R-SiamNet with instance-level consistency loss and cluster-level contrastive loss. For instance-level consistency learning, the R-SiamNet is constrained to extract consistent features from each person region with or without out-of-region context. For cluster-level contrastive learning, we enforce the aggregation of closest instances and the separation of dissimilar ones in feature space. Extensive experiments validate the utility of our weakly supervised method. Our model achieves the rank-1 of 87.1% and mAP of 86.0% on CUHK-SYSU benchmark, which surpasses several fully supervised methods, such as OIM and MGTS, by a clear margin. More promising performance can be reached by incorporating extra training data. We hope this work could encourage the future research in this field.

Related papers

• Hierarchical Point-based Active Learning for Semi-supervised Point Cloud Semantic Segmentation [48.40853126077237]
  It is labour-intensive to acquire large-scale point cloud data with point-wise labels. Active learning is one of the effective strategies to achieve this purpose but is still under-explored. This paper develops a hierarchical point-based active learning strategy.
  arXiv  Detail & Related papers  (2023-08-22T03:52:05Z)
• Nearest Neighbor-Based Contrastive Learning for Hyperspectral and LiDAR Data Classification [45.026868970899514]
  We propose a Nearest Neighbor-based Contrastive Learning Network (NNCNet) to learn discriminative feature representations. Specifically, we propose a nearest neighbor-based data augmentation scheme to use enhanced semantic relationships among nearby regions. In addition, we design a bilinear attention module to exploit the second-order and even high-order feature interactions between the HSI and LiDAR data.
  arXiv  Detail & Related papers  (2023-01-09T13:43:54Z)
• Ladder Siamese Network: a Method and Insights for Multi-level Self-Supervised Learning [9.257121691188008]
  Siamese-network-based self-supervised learning (SSL) suffers from slow convergence and instability in training. We propose a framework to exploit intermediate self-supervisions in each stage of deep nets, called the Ladder Siamese Network.
  arXiv  Detail & Related papers  (2022-11-25T00:49:25Z)
• Self-Ensembling GAN for Cross-Domain Semantic Segmentation [107.27377745720243]
  This paper proposes a self-ensembling generative adversarial network (SE-GAN) exploiting cross-domain data for semantic segmentation. In SE-GAN, a teacher network and a student network constitute a self-ensembling model for generating semantic segmentation maps, which together with a discriminator, forms a GAN. Despite its simplicity, we find SE-GAN can significantly boost the performance of adversarial training and enhance the stability of the model.
  arXiv  Detail & Related papers  (2021-12-15T09:50:25Z)
• Going Deeper into Semi-supervised Person Re-identification [12.37129078618206]
  We focus on a semi-supervised approach that requires only a subset of the training data to be labeled. Our method outperforms the state-of-the-art results on three large-scale person re-id datasets.
  arXiv  Detail & Related papers  (2021-07-24T09:28:13Z)
• Semi-supervised Left Atrium Segmentation with Mutual Consistency Training [60.59108570938163]
  We propose a novel Mutual Consistency Network (MC-Net) for semi-supervised left atrium segmentation from 3D MR images. Our MC-Net consists of one encoder and two slightly different decoders, and the prediction discrepancies of two decoders are transformed as an unsupervised loss. We evaluate our MC-Net on the public Left Atrium (LA) database and it obtains impressive performance gains by exploiting the unlabeled data effectively.
  arXiv  Detail & Related papers  (2021-03-04T09:34:32Z)
• 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)
• Region Comparison Network for Interpretable Few-shot Image Classification [97.97902360117368]
  Few-shot image classification has been proposed to effectively use only a limited number of labeled examples to train models for new classes. We propose a metric learning based method named Region Comparison Network (RCN), which is able to reveal how few-shot learning works. We also present a new way to generalize the interpretability from the level of tasks to categories.
  arXiv  Detail & Related papers  (2020-09-08T07:29:05Z)
• Unsupervised Feature Learning by Cross-Level Instance-Group Discrimination [68.83098015578874]
  We integrate between-instance similarity into contrastive learning, not directly by instance grouping, but by cross-level discrimination. CLD effectively brings unsupervised learning closer to natural data and real-world applications. New state-of-the-art on self-supervision, semi-supervision, and transfer learning benchmarks, and beats MoCo v2 and SimCLR on every reported performance.
  arXiv  Detail & Related papers  (2020-08-09T21:13:13Z)

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.