Attention driven person re-identification

Abstract

Person re-identification (ReID) is a challenging task due to arbitrary human pose variations, background clutters, etc. It has been studied extensively in recent years, but the multifarious local and global features are still not fully exploited by either ignoring the interplay between whole-body images and body-part images or missing in-depth examination of specific body-part images. In this paper, we propose a novel attention-driven multi-branch network that learns robust and discriminative human representation from global whole-body images and local body-part images simultaneously. Within each branch, an intra-attention network is designed to search for informative and discriminative regions within the whole-body or body-part images, where attention is elegantly decomposed into spatial-wise attention and channel-wise attention for effective and efficient learning. In addition, a novel inter-attention module is designed which fuses the output of intra-attention networks adaptively for optimal person ReID. The proposed technique has been evaluated over three widely used datasets CUHK03, Market-1501 and DukeMTMC-ReID, and experiments demonstrate its superior robustness and effectiveness as compared with the state of the arts.

VMRFANet: View-specific Multi-Receptive Field Attention Network for Person Re-identification

“…For example, (Cai et al, 2019) utilized body masks to guide the training of attention module. (Yang et al, 2019) proposed an end-to-end trainable framework composed of local and fusion attention modules that can incorporate im-age partition using human key-points estimation. Our proposed MRFA module is designed to address the imperfect detection issue mentioned above.…”

“…DukeMTMC-reID rank 1 mAP rank 1 mAP SVDNet 82.3 62.1 76.7 56.8 PAN 82.8 63.4 71.6 51.5 MultiScale (Chen et al, 2017) 88.9 73.1 79.2 60.6 MLFN (Chang et al, 2018) 90.0 74.3 81.0 62.8 HA-CNN (Li et al, 2018) 91.2 75.7 80.5 63.8 Mancs (Wang et al, 2018a) 93.1 82.3 84.9 71.8 Attention-Driven (Yang et al, 2019) 94.9 86.4 86.0 74.5 PCB+RPP (Sun et al, 2018) 93.8 81.6 83.3 69.2 HPM (Fu et al, 2018) 94.2 82.7 86.6 74.3 MGN (Wang et al, 2018b) 95.7 86.9 88.7 78.4 VMRFANet(Ours) 95.5 88.1 88.9 80.0 Table 3: Comparison of results on CUHK03-labeled (CUHK03-L) and CUHK03-detected (CUHK03-D) with new protocol (Zhong et al, 2017a). The best results are in bold, while the numbers with underlines denote the second best.…”

“…Other strategies such as partition based on human pose (e.g. (Yang et al, 2019)) often introduce side models trained on different datasets. In that case, domain bias may come into play.…”

Multi-Scale Body-Part Mask Guided Attention for Person Re-Identification

“…Visual attention has shown its success in re-ID tasks [42,22,29,19], as the mechanism conforms to the human visual system that a whole image is not likely to be processed in its entirety at once, but only the salient parts of the whole visual space are focused when and where needed. Visual attention module can help to extract dynamic features from salient parts mostly like human body parts in a image by guiding the learning towards informative image regions [29].…”

“…Visual attention module can help to extract dynamic features from salient parts mostly like human body parts in a image by guiding the learning towards informative image regions [29]. Given the human body information, attention maps where regions of interest are presented have much stronger responses on body region compared with background regions [22,42]. Inspired by this, whole human body mask has been used to guide the attention model training [29].…”