# AaP-ReID: Improved Attention-Aware Person Re-identification

arXiv: https://arxiv.org/abs/2309.15780 · HTML: https://mlsanity.com/paper/2309.15780/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 37 references that are in the map.
- First posted on arXiv 27 Sep 2023.

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking](https://mlsanity.com/paper/1609.01775/) (2016)
- [ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks](https://mlsanity.com/paper/1910.03151/) (2019)
- [Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)](https://mlsanity.com/paper/1711.09349/) (2017)
- [Re-ranking Person Re-identification with k-reciprocal Encoding](https://mlsanity.com/paper/1701.08398/) (2017)
- [Person Re-identification: Past, Present and Future](https://mlsanity.com/paper/1610.02984/) (2016)
- [BAM: Bottleneck Attention Module](https://mlsanity.com/paper/1807.06514/) (2018)
- [Style Normalization and Restitution for Generalizable Person Re-identification](https://mlsanity.com/paper/2005.11037/) (2020)
- [High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification](https://mlsanity.com/paper/2003.08177/) (2020)
- [Improving Person Re-identification by Attribute and Identity Learning](https://mlsanity.com/paper/1703.07220/) (2017)
- [Body Part-Based Representation Learning for Occluded Person Re-Identification](https://mlsanity.com/paper/2211.03679/) (2022)
- [Camera-aware Proxies for Unsupervised Person Re-Identification](https://mlsanity.com/paper/2012.10674/) (2020)
- [Densely Semantically Aligned Person Re-Identification](https://mlsanity.com/paper/1812.08967/) (2018)
- [Deep learning-based person re-identification methods: A survey and outlook of recent works](https://mlsanity.com/paper/2110.04764/) (2021)
- [Person Re-identification with Metric Learning using Privileged Information](https://mlsanity.com/paper/1904.05005/) (2019)
- [Faster Person Re-Identification](https://mlsanity.com/paper/2008.06826/) (2020)
- [Attention-Aware Generalized Mean Pooling for Image Retrieval](https://mlsanity.com/paper/1811.00202/) (2018)
- [YOLORe-IDNet: An Efficient Multi-Camera System for Person-Tracking](https://mlsanity.com/paper/2309.13387/) (2023)

## Abstract (arXiv)

Person re-identification (ReID) is a well-known problem in the field of computer vision. The primary objective is to identify a specific individual within a gallery of images. However, this task is challenging due to various factors, such as pose variations, illumination changes, obstructions, and the presence ofconfusing backgrounds. Existing ReID methods often fail to capture discriminative features (e.g., head, shoes, backpacks) and instead capture irrelevant features when the target is occluded. Motivated by the success of part-based and attention-based ReID methods, we improve AlignedReID++ and present AaP-ReID, a more effective method for person ReID that incorporates channel-wise attention into a ResNet-based architecture. Our method incorporates the Channel-Wise Attention Bottleneck (CWAbottleneck) block and can learn discriminating features by dynamically adjusting the importance ofeach channel in the feature maps. We evaluated Aap-ReID on three benchmark datasets: Market-1501, DukeMTMC-reID, and CUHK03. When compared with state-of-the-art person ReID methods, we achieve competitive results with rank-1 accuracies of 95.6% on Market-1501, 90.6% on DukeMTMC-reID, and 82.4% on CUHK03.