Re-Identification With Consistent Attentive Siamese Networks

Abstract

We propose a new deep architecture for person reidentification (re-id). While re-id has seen much recent progress, spatial localization and view-invariant representation learning for robust cross-view matching remain key, unsolved problems. We address these questions by means of a new attention-driven Siamese learning architecture, called the Consistent Attentive Siamese Network. Our key innovations compared to existing, competing methods include (a) a flexible framework design that produces attention with only identity labels as supervision, (b) explicit mechanisms to enforce attention consistency among images of the same person, and (c) a new Siamese framework that integrates attention and attention consistency, producing principled supervisory signals as well as the first mechanism that can explain the reasoning behind the Siamese framework's predictions. We conduct extensive evaluations on the CUHK03-NP, DukeMTMC-ReID, and Market-1501 datasets and report competitive performance.

Progressive Cross-Camera Soft-Label Learning for Semi-Supervised Person Re-Identification

“…Currently, most existing work for person Re-ID mainly focuses on the supervised [5], [6], [7], [8] and unsupervised [9], [10], [11], [12], [13] cases. Although the supervised Lei Comparison between inter-camera and intra-camera images on Market1501 [4].…”

Discriminative Spatial Feature Learning for Person Re-Identification

“…We compare the proposed method with 33 recent published works including (1) global feature based methods which aims to learn the global feature from the feature map directly, including PAN [74], DMML [7], DCDS [1], VCFL [30], MVPM [41], LRDNN [79], RB [35], LITM [63], IANet [23], Sphere [14], BNNeck [32], OSNet [78], AANet [46], DG-Net [72], BDB [12], Circle [42], SFT [31], (2) part based methods including PCB+RPP [43], Local [57], HPM [16], CASN [71], AutoReID [34], MGN [49], BHP [20] and Pyramidal [68] which utilize the semantic parts or horizontal stripes to extract part-level feature, and (3) attention based methods including MHAN [3], CAMA [58], SONA [53], CAR [80], SCAL [6], ABD-Net [8], DAAF [10] and RGA [65]. These methods are categorized into 3 types based on different backbones: the ones which employ ResNet-50 directly, the ones which modify ResNet-50 by introducing additional branches, attention subnets or dilated convolution, and the others which don't use ResNet-50.…”

“…We mainly review the former which utilize deep learning to extract the feature. Holistic Features Based Methods Given a backbone C-NN such as ResNet-50 [21] or other network architectures [2,51,71,78], this type of methods learns discriminative holistic features from the feature map directly. Specifically, they aim to learn the features by improving loss functions [9,14,22,31,41,42,50,55,63], improving the training techniques [1,4,12,24,32,35,37,54], adding additional network modules [23,23,51,62], using extra semantic annotations [30,46,47,79] or generating more training samples [17,33,72,76,77].…”

MSBA: Multiple Scales, Branches and Attention Network With Bag of Tricks for Person Re-Identification

“…This approach is capable of extracting information from an image by adaptively selecting the most informative image regions and only processing the selected regions at high resolution. Zheng et al [21] proposed a new attention-driven Siamese learning framework, called the Consistent Attentive Siamese Network (CASN). The framework uses the original ID signal to guide the model to find consistent attention areas for images of the same identity, and also learns the identityaware constant representation for cross-view matching.…”