Sharp Attention Network via Adaptive Sampling for Person Re-identification
This work addresses the problem of improving person re-identification accuracy for surveillance and security applications, presenting a novel method that is incremental but offers specific gains.
The paper tackles person re-identification by proposing sharp attention networks that adaptively sample feature maps to generate sharper attention masks, resulting in superior performance over state-of-the-art methods on benchmarks like CUHK03, Market-1501, and DukeMTMC-reID.
In this paper, we present novel sharp attention networks by adaptively sampling feature maps from convolutional neural networks (CNNs) for person re-identification (re-ID) problem. Due to the introduction of sampling-based attention models, the proposed approach can adaptively generate sharper attention-aware feature masks. This greatly differs from the gating-based attention mechanism that relies soft gating functions to select the relevant features for person re-ID. In contrast, the proposed sampling-based attention mechanism allows us to effectively trim irrelevant features by enforcing the resultant feature masks to focus on the most discriminative features. It can produce sharper attentions that are more assertive in localizing subtle features relevant to re-identifying people across cameras. For this purpose, a differentiable Gumbel-Softmax sampler is employed to approximate the Bernoulli sampling to train the sharp attention networks. Extensive experimental evaluations demonstrate the superiority of this new sharp attention model for person re-ID over the other state-of-the-art methods on three challenging benchmarks including CUHK03, Market-1501, and DukeMTMC-reID.