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

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.

arXiv comment11 pages, 6 figures. Accepted for publication in IEEE Transactions on Image Processing 2021

References in corpus (10)

• Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks
• Learning Discriminative Features with Multiple Granularities for Person Re-Identification
• Random Erasing Data Augmentation
• Particular object retrieval with integral max-pooling of CNN activations
• Aggregating Deep Convolutional Features for Image Retrieval
• Robust Depth-based Person Re-identification
• SVDNet for Pedestrian Retrieval
• Stripe-based and Attribute-aware Network: A Two-Branch Deep Model for Vehicle Re-identification
• Deep Learning for Person Re-identification: A Survey and Outlook
• Learning Deep Neural Networks for Vehicle Re-ID with Visual-spatio-temporal Path Proposals