Second-order Non-local Attention Networks for Person Re-identification

Abstract

Recent efforts have shown promising results for person re-identification by designing part-based architectures to allow a neural network to learn discriminative representations from semantically coherent parts. Some efforts use soft attention to reallocate distant outliers to their most similar parts, while others adjust part granularity to incorporate more distant positions for learning the relationships. Others seek to generalize part-based methods by introducing a dropout mechanism on consecutive regions of the feature map to enhance distant region relationships. However, only few prior efforts model the distant or non-local positions of the feature map directly for the person re-ID task. In this paper, we propose a novel attention mechanism to directly model long-range relationships via second-order feature statistics. When combined with a generalized DropBlock module, our method performs equally to or better than state-of-the-art results for mainstream person re-identification datasets, including Market1501, CUHK03, and DukeMTMC-reID.

arXiv commentICCV 2019

References in corpus (14)

• Adam: A Method for Stochastic Optimization
• In Defense of the Triplet Loss for Person Re-Identification
• Improved Regularization of Convolutional Neural Networks with Cutout
• Pedestrian Alignment Network for Large-scale Person Re-identification
• DropBlock: A regularization method for convolutional networks
• Deep Representation Learning with Part Loss for Person Re-Identification
• GLAD: Global-Local-Alignment Descriptor for Pedestrian Retrieval
• Deep Transfer Learning for Person Re-identification
• Looking Beyond Appearances: Synthetic Training Data for Deep CNNs in Re-identification
• Bag of Tricks for Image Classification with Convolutional Neural Networks
• Compact Generalized Non-local Network
• Person Re-Identification by Deep Joint Learning of Multi-Loss Classification
• Pyramidal Person Re-IDentification via Multi-Loss Dynamic Training
• Batch DropBlock Network for Person Re-identification and Beyond

Cited by in corpus (7)

• Person Re-identification via Attention Pyramid
• TransReID: Transformer-based Object Re-Identification
• Learning to Disentangle Scenes for Person Re-identification
• DSSL: Deep Surroundings-person Separation Learning for Text-based Person Retrieval
• A Challenging Benchmark of Anime Style Recognition
• Dual Gaussian-based Variational Subspace Disentanglement for Visible-Infrared Person Re-Identification
• FTN: Foreground-Guided Texture-Focused Person Re-Identification