ES-Net: Erasing Salient Parts to Learn More in Re-Identification

• URL: http://arxiv.org/abs/2103.05918v1
• Date: Wed, 10 Mar 2021 08:19:46 GMT
• Title: ES-Net: Erasing Salient Parts to Learn More in Re-Identification
• Authors: Dong Shen, Shuai Zhao, Jinming Hu, Hao Feng, Deng Cai, Xiaofei He
• Abstract summary: We propose a novel network, Erasing-Salient Net (ES-Net), to learn comprehensive features by erasing the salient areas in an image. Our ES-Net outperforms state-of-the-art methods on three Person re-ID benchmarks and two Vehicle re-ID benchmarks.
• Score: 46.624740579314924
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As an instance-level recognition problem, re-identification (re-ID) requires models to capture diverse features. However, with continuous training, re-ID models pay more and more attention to the salient areas. As a result, the model may only focus on few small regions with salient representations and ignore other important information. This phenomenon leads to inferior performance, especially when models are evaluated on small inter-identity variation data. In this paper, we propose a novel network, Erasing-Salient Net (ES-Net), to learn comprehensive features by erasing the salient areas in an image. ES-Net proposes a novel method to locate the salient areas by the confidence of objects and erases them efficiently in a training batch. Meanwhile, to mitigate the over-erasing problem, this paper uses a trainable pooling layer P-pooling that generalizes global max and global average pooling. Experiments are conducted on two specific re-identification tasks (i.e., Person re-ID, Vehicle re-ID). Our ES-Net outperforms state-of-the-art methods on three Person re-ID benchmarks and two Vehicle re-ID benchmarks. Specifically, mAP / Rank-1 rate: 88.6% / 95.7% on Market1501, 78.8% / 89.2% on DuckMTMC-reID, 57.3% / 80.9% on MSMT17, 81.9% / 97.0% on Veri-776, respectively. Rank-1 / Rank-5 rate: 83.6% / 96.9% on VehicleID (Small), 79.9% / 93.5% on VehicleID (Medium), 76.9% / 90.7% on VehicleID (Large), respectively. Moreover, the visualized salient areas show human-interpretable visual explanations for the ranking results.

Related papers

• AaP-ReID: Improved Attention-Aware Person Re-identification [2.5761958263376745]
  AaP-ReID is a more effective method for person ReID that incorporates channel-wise attention into a ResNet-based architecture. Our method incorporates the Channel-Wise Attention Bottleneck block and can learn discriminating features by dynamically adjusting the importance ofeach channel in the feature maps.
  arXiv  Detail & Related papers  (2023-09-27T16:54:38Z)
• From Global to Local: Multi-scale Out-of-distribution Detection [129.37607313927458]
  Out-of-distribution (OOD) detection aims to detect "unknown" data whose labels have not been seen during the in-distribution (ID) training process. Recent progress in representation learning gives rise to distance-based OOD detection. We propose Multi-scale OOD DEtection (MODE), a first framework leveraging both global visual information and local region details.
  arXiv  Detail & Related papers  (2023-08-20T11:56:25Z)
• Body Part-Based Representation Learning for Occluded Person Re-Identification [102.27216744301356]
  Occluded person re-identification (ReID) is a person retrieval task which aims at matching occluded person images with holistic ones. Part-based methods have been shown beneficial as they offer fine-grained information and are well suited to represent partially visible human bodies. We propose BPBreID, a body part-based ReID model for solving the above issues.
  arXiv  Detail & Related papers  (2022-11-07T16:48:41Z)
• A High-Accuracy Unsupervised Person Re-identification Method Using Auxiliary Information Mined from Datasets [53.047542904329866]
  We make use of auxiliary information mined from datasets for multi-modal feature learning. This paper proposes three effective training tricks, including Restricted Label Smoothing Cross Entropy Loss (RLSCE), Weight Adaptive Triplet Loss (WATL) and Dynamic Training Iterations (DTI)
  arXiv  Detail & Related papers  (2022-05-06T10:16:18Z)
• Learning Instance-level Spatial-Temporal Patterns for Person Re-identification [80.43222559182072]
  We propose a novel Instance-level and Spatial-temporal Disentangled Re-ID method (InSTD) to improve Re-ID accuracy. In our proposed framework, personalized information such as moving direction is explicitly considered to further narrow down the search space. The proposed method achieves mAP of 90.8% on Market-1501 and 89.1% on DukeMTMC-reID, improving from the baseline 82.2% and 72.7%, respectively.
  arXiv  Detail & Related papers  (2021-07-31T07:44:47Z)
• Multi-Attribute Enhancement Network for Person Search [7.85420914437147]
  Person Search is designed to jointly solve the problems of Person Detection and Person Re-identification (Re-ID) Visual character attributes play a key role in retrieving the query person, which has been explored in Re-ID but has been ignored in Person Search. We introduce attribute learning into the model, allowing the use of attribute features for retrieval task.
  arXiv  Detail & Related papers  (2021-02-16T05:43:47Z)
• Unsupervised Pre-training for Person Re-identification [90.98552221699508]
  We present a large scale unlabeled person re-identification (Re-ID) dataset "LUPerson" We make the first attempt of performing unsupervised pre-training for improving the generalization ability of the learned person Re-ID feature representation.
  arXiv  Detail & Related papers  (2020-12-07T14:48:26Z)
• Grafted network for person re-identification [14.372506245952383]
  Convolutional neural networks have shown outstanding effectiveness in person re-identification (re-ID) We propose a novel grafted network (GraftedNet), which is designed by grafting a high-accuracy rootstock and a light-weighted scion. Experimental results show that the proposed GraftedNet achieves 93.02%, 85.3% and 76.2% in Rank-1 and 81.6%, 74.7% and 71.6% in mAP, with only 4.6M parameters.
  arXiv  Detail & Related papers  (2020-06-02T22:33:44Z)
• VMRFANet:View-Specific Multi-Receptive Field Attention Network for Person Re-identification [3.1498833540989413]
  We propose a novel multi-receptive field attention (MRFA) module that utilizes filters of various sizes to help network focusing on informative pixels. We present a view-specific mechanism that guides attention module to handle the variation of view conditions. Our method achieves 95.5% / 88.1% in rank-1 / mAP on Market-1501, 88.9% / 80.0% on DukeMTMC-reID, 81.1% / 78.8% on CUHK03 labeled dataset and 78.9% / 75.3% on CUHK03 detected dataset.
  arXiv  Detail & Related papers  (2020-01-21T06:31:18Z)

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.