Mixed High-Order Attention Network for Person Re-Identification

By Binghui Chen, Weihong Deng, Jiani Hu. IEEE International Conference on Computer Vision, 2019

399 citations recorded by the source corpus.

Attention has become more attractive in person re-identification (ReID) as it is capable of biasing the allocation of available resources towards the most informative parts of an input signal. However, state-of-the-art works concentrate only on coarse or first-order attention design, e.g. spatial and channels attention, while rarely exploring higher-order attention mechanism. We take a step towards addressing this problem. In this paper, we first propose the High-Order Attention (HOA) module to model and utilize the complex and high-order statistics information in attention mechanism, so as to capture the subtle differences among pedestrians and to produce the discriminative attention proposals. Then, rethinking person ReID as a zero-shot learning problem, we propose the Mixed High-Order Attention Network (MHN) to further enhance the discrimination and richness of attention knowledge in an explicit manner. Extensive experiments have been conducted to validate the superiority of our MHN for person ReID over a wide variety of state-of-the-art methods on three large-scale datasets, including Market-1501, DukeMTMC-ReID and CUHK03-NP. Code is available at http://www.bhchen.cn.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/061f205009b39438e39448164064233162884252

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Dynamic Dual-Attentive Aggregation Learning for Visible-Infrared Person Re-Identification (2020, background): “Person re-identification (Re-ID) techniques [59,68] have achieved human-level performance with part-level deep feature learning [4,40,67].”
Attention mechanisms in computer vision: A survey (2021, background): “segmentation [156, 40], face recognition [145, 126], person re-identification [78, 14], action recognition [128, 37], few-show learning [103, 58], medical image processing [99, 47], image generation [46, 159], pose estimation [27], super resolution [30, 164], 3D vision [137, 48], and multi-modal tas”
Identity-Guided Human Semantic Parsing for Person Re-Identification (2020, methodology): “From (a) to (d): AlignedReID [52], MSCAN [20], DPL [51], MHN [3].”
Relation-Aware Global Attention for Person Re-Identification (2019, background): “Recently, many studies resort to attention design to address the aforementioned challenges in person re-id by strengthening the discriminative features and suppressing interference [22, 39, 20, 12, 11, 6].”
Visual Attention Methods in Deep Learning: An In-Depth Survey (2022, background): “SE [26], CBAM [25], splat [23], mixed [74].”