# A Little Bit Attention Is All You Need for Person Re-Identification

arXiv: https://arxiv.org/abs/2302.14574 · HTML: https://mlsanity.com/paper/2302.14574/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 68 references that are in the map.
- First posted on arXiv 28 Feb 2023.

## Builds on (most cited first, 30 of 31)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](https://mlsanity.com/paper/1807.11164/) (2018)
- [Designing Network Design Spaces](https://mlsanity.com/paper/2003.13678/) (2020)
- [Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking](https://mlsanity.com/paper/1609.01775/) (2016)
- [Deep Learning for Person Re-identification: A Survey and Outlook](https://mlsanity.com/paper/2001.04193/) (2020)
- [Bag of Tricks and A Strong Baseline for Deep Person Re-identification](https://mlsanity.com/paper/1903.07071/) (2019)
- [Circle Loss: A Unified Perspective of Pair Similarity Optimization](https://mlsanity.com/paper/2002.10857/) (2020)
- [Residual Attention Network for Image Classification](https://mlsanity.com/paper/1704.06904/) (2017)
- [Harmonious Attention Network for Person Re-Identification](https://mlsanity.com/paper/1802.08122/) (2018)
- [ABD-Net: Attentive but Diverse Person Re-Identification](https://mlsanity.com/paper/1908.01114/) (2019)
- [Relation-Aware Global Attention for Person Re-identification](https://mlsanity.com/paper/1904.02998/) (2019)
- [Dynamic Dual-Attentive Aggregation Learning for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2007.09314/) (2020)
- [Mixed High-Order Attention Network for Person Re-Identification](https://mlsanity.com/paper/1908.05819/) (2019)
- [AANet: Attribute Attention Network for Person Re-Identifications](https://mlsanity.com/paper/1912.09021/) (2019)
- [Diversity Regularized Spatiotemporal Attention for Video-based Person Re-identification](https://mlsanity.com/paper/1803.09882/) (2018)
- [Dual Attention Matching Network for Context-Aware Feature Sequence based Person Re-Identification](https://mlsanity.com/paper/1803.09937/) (2018)
- [Attention-Aware Compositional Network for Person Re-identification](https://mlsanity.com/paper/1805.03344/) (2018)
- [STA: Spatial-Temporal Attention for Large-Scale Video-based Person Re-Identification](https://mlsanity.com/paper/1811.04129/) (2018)
- [Spatial-Temporal Person Re-identification](https://mlsanity.com/paper/1812.03282/) (2018)
- [Multi-Granularity Reference-Aided Attentive Feature Aggregation for Video-based Person Re-identification](https://mlsanity.com/paper/2003.12224/) (2020)
- [Second-order Non-local Attention Networks for Person Re-identification](https://mlsanity.com/paper/1909.00295/) (2019)
- [Recurrent Attention Models for Depth-Based Person Identification](https://mlsanity.com/paper/1611.07212/) (2016)
- [Deep Transfer Learning for Person Re-identification](https://mlsanity.com/paper/1611.05244/) (2016)
- [Attention Driven Person Re-identification](https://mlsanity.com/paper/1810.05866/) (2018)
- [Discriminative Feature Learning with Foreground Attention for Person Re-Identification](https://mlsanity.com/paper/1807.01455/) (2018)
- [Person Following by Autonomous Robots: A Categorical Overview](https://mlsanity.com/paper/1803.08202/) (2018)

## Built on by (most cited first, 1 of 1)

- [Iterative Optimal Attention and Local Model for Single Image Rain Streak Removal](https://mlsanity.com/paper/2503.16165/) (2025)

## Abstract (arXiv)

Person re-identification plays a key role in applications where a mobile robot needs to track its users over a long period of time, even if they are partially unobserved for some time, in order to follow them or be available on demand. In this context, deep-learning based real-time feature extraction on a mobile robot is often performed on special-purpose devices whose computational resources are shared for multiple tasks. Therefore, the inference speed has to be taken into account. In contrast, person re-identification is often improved by architectural changes that come at the cost of significantly slowing down inference. Attention blocks are one such example. We will show that some well-performing attention blocks used in the state of the art are subject to inference costs that are far too high to justify their use for mobile robotic applications. As a consequence, we propose an attention block that only slightly affects the inference speed while keeping up with much deeper networks or more complex attention blocks in terms of re-identification accuracy. We perform extensive neural architecture search to derive rules at which locations this attention block should be integrated into the architecture in order to achieve the best trade-off between speed and accuracy. Finally, we confirm that the best performing configuration on a re-identification benchmark also performs well on an indoor robotic dataset.