AANet: Attribute Attention Network for Person Re-Identifications

Abstract

This paper proposes Attribute Attention Network (AANet), a new architecture that integrates person attributes and attribute attention maps into a classification framework to solve the person re-identification (re-ID) problem. Many person re-ID models typically employ semantic cues such as body parts or human pose to improve the re-ID performance. Attribute information, however, is often not utilized. The proposed AANet leverages on a baseline model that uses body parts and integrates the key attribute information in an unified learning framework. The AANet consists of a global person ID task, a part detection task and a crucial attribute detection task. By estimating the class responses of individual attributes and combining them to form the attribute attention map (AAM), a very strong discriminatory representation is constructed. The proposed AANet outperforms the best state-of-the-art method [22] using ResNet-50 by 3.36% in mAP and 3.12% in Rank-1 accuracy on DukeMTMC-reID dataset. On Market1501 dataset, AANet achieves 92.38% mAP and 95.10% Rank-1 accuracy with re-ranking, outperforming [13], another state of the art method using ResNet-152, by 1.42% in mAP and 0.47% in Rank-1 accuracy. In addition, AANet can perform person attribute prediction (e.g., gender, hair length, clothing length etc.), and localize the attributes in the query image.

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.…”

“…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]. Besides, more recent studies [3,6,8,10,27,28,38,46,48,53,58,61,64,…”

Beyond Human Parts: Dual Part-Aligned Representations for Person Re-Identification

“…Semantic attributes [46,25,7] have been exploited as feature representations for person reidentification tasks. Previous work [47,6,20,42,58] leverages the attribute labels provided by original dataset to generate attribute-aware feature representation. Different from previous work, our latent part branch can attend to important visual cues without relying on detailed supervision signals from the limited predefined attributes.…”

Unsupervised Person Re-identification via Cross-Camera Similarity Exploration

“…Most re-ID methods are in a supervised manner, in which sufficient labeled images are given. Recently, with the developing of deep learning approaches [36,35,34], methods with convolutional neural networks have dominated the re-ID community [12,26,45,46,25,16]. Specifically, methods proposed to learn discriminative features from parts of pedestrian images achieve impressive performance [24,8,23].…”

“…Given a query image, person re-identification (re-ID) aims to match the person across multiple non-overlapped cameras. In the last few years, person re-ID has drawn increasing research attention [12,45,46,25,24,23], due to its wide range of applications such as finding people of interest (e.g., lost kids or criminals) and person tracking. However, most of the proposed methods are of supervised manner, which requires intensive manual labeling and is not applicable to real-world applications.…”