End-to-End Comparative Attention Networks for Person Re-Identification

Abstract

Abstract-Person re-identification across disjoint camera views has been widely applied in video surveillance yet it is still a challenging problem. One of the major challenges lies in the lack of spatial and temporal cues, which makes it difficult to deal with large variations of lighting conditions, viewing angles, body poses and occlusions. Recently, several deep learning based person re-identification approaches have been proposed and achieved remarkable performance. However, most of those approaches extract discriminative features from the whole frame at one glimpse without differentiating various parts of the persons to identify. It is essentially important to examine multiple highly discriminative local regions of the person images in details through multiple glimpses for dealing with the large appearance variance.In this paper, we propose a new soft attention based model, i.e., the end-to-end Comparative Attention Network (CAN), specifically tailored for the task of person re-identification. The end-to-end CAN learns to selectively focus on parts of pairs of person images after taking a few glimpses of them and adaptively comparing their appearance. The CAN model is able to learn which parts of images are relevant for discerning persons and automatically integrates information from different parts to determine whether a pair of images belongs to the same person. In other words, our proposed CAN model simulates the human perception process to verify whether two images are from the same person. Extensive experiments on four benchmark person re-identification datasets, including CUHK01, CHUHK03, Market-1501 and VIPeR, clearly demonstrate that our proposed end-to-end CAN for person re-identification outperforms well established baselines significantly and offer new state-of-the-art performance.

Impostor Resilient Multimodal Metric Learning for Person Reidentification

“…Only K-LFDA when trained with mom LE [24] feature attains comparable performance than DMN. However, motivated to resolve the challenges for reidentification in real world (i.e., multimodal image space, and diverse impostors) IRM3 + CVI ( = 15) has much better results than MCP-CNN [39], E2E-CAN [31], Quadruplet-Net [33], and JLML [34], while our IRM3 + CVI ( = 15) has 1.49% higher rank@1 than DLPA [32]. DLPA extracts deep features by semantically aligning body parts, as well as rectifying pose variations.…”

FMT: fusing multi-task convolutional neural network for person search

“…Deep learning is very extensive. Some works [15] [16] [17] also propose person re-identification methods based on deep learning, which design the structure of deep learning network to improve the performance of their methods. Multi-task learning is raised because we focus on a single task, and ignore other information that might help optimize metrics.…”

Video-Based Convolutional Attention for Person Re-Identification

“…These models assign weights to different parts of each frame, making some of them more important than others. In particular, [12] proposes integrating a spatial attention based model in a siamese network to adaptively focus on the important local parts of an input image pair.…”

“…Nevertheless there are relatively few attempts to use Attention in the field of Automatic Re-Identification. [12] proposes integrating a soft attention based model in a Siamese network to focus adaptively on the important local regions of an input image pair. [13] uses a spatial pyramid layer as the component attentive spatial pooling to select important regions in spatial dimension.…”