# Weakly-supervised Part-Attention and Mentored Networks for Vehicle Re-Identification

arXiv: https://arxiv.org/abs/2107.08228 · HTML: https://mlsanity.com/paper/2107.08228/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 44 references that are in the map.
- First posted on arXiv 17 Jul 2021.

## Builds on (most cited first, 26 of 26)

- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [In Defense of the Triplet Loss for Person Re-Identification](https://mlsanity.com/paper/1703.07737/) (2017)
- [Bag of Tricks and A Strong Baseline for Deep Person Re-identification](https://mlsanity.com/paper/1903.07071/) (2019)
- [Re-ranking Person Re-identification with k-reciprocal Encoding](https://mlsanity.com/paper/1701.08398/) (2017)
- [Harmonious Attention Network for Person Re-Identification](https://mlsanity.com/paper/1802.08122/) (2018)
- [HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis](https://mlsanity.com/paper/1709.09930/) (2017)
- [Densely Semantically Aligned Person Re-Identification](https://mlsanity.com/paper/1812.08967/) (2018)
- [Parsing-based View-aware Embedding Network for Vehicle Re-Identification](https://mlsanity.com/paper/2004.05021/) (2020)
- [Selective Convolutional Descriptor Aggregation for Fine-Grained Image Retrieval](https://mlsanity.com/paper/1604.04994/) (2016)
- [Deep Representation Learning with Part Loss for Person Re-Identification](https://mlsanity.com/paper/1707.00798/) (2017)
- [The Devil is in the Details: Self-Supervised Attention for Vehicle Re-Identification](https://mlsanity.com/paper/2004.06271/) (2020)
- [Exploring Spatial Significance via Hybrid Pyramidal Graph Network for Vehicle Re-identification](https://mlsanity.com/paper/2005.14684/) (2020)
- [RAM: A Region-Aware Deep Model for Vehicle Re-Identification](https://mlsanity.com/paper/1806.09283/) (2018)
- [Pedestrian Alignment Network for Large-scale Person Re-identification](https://mlsanity.com/paper/1707.00408/) (2017)
- [Orientation-aware Vehicle Re-identification with Semantics-guided Part Attention Network](https://mlsanity.com/paper/2008.11423/) (2020)
- [Multi-task Learning with Coarse Priors for Robust Part-aware Person Re-identification](https://mlsanity.com/paper/2003.08069/) (2020)
- [Stripe-based and Attribute-aware Network: A Two-Branch Deep Model for Vehicle Re-identification](https://mlsanity.com/paper/1910.05549/) (2019)
- [Batch Coherence-Driven Network for Part-aware Person Re-Identification](https://mlsanity.com/paper/2009.09692/) (2020)
- [CDPM: Convolutional Deformable Part Models for Semantically Aligned Person Re-identification](https://mlsanity.com/paper/1906.04976/) (2019)
- [Moving Towards Centers: Re-ranking with Attention and Memory for Re-identification](https://mlsanity.com/paper/2105.01447/) (2021)
- [Factorized Distillation: Training Holistic Person Re-identification Model by Distilling an Ensemble of Partial ReID Models](https://mlsanity.com/paper/1811.08073/) (2018)

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

- [OccluTrack: Rethinking Awareness of Occlusion for Enhancing Multiple Pedestrian Tracking](https://mlsanity.com/paper/2309.10360/) (2023)

## Abstract (arXiv)

Vehicle re-identification (Re-ID) aims to retrieve images with the same vehicle ID across different cameras. Current part-level feature learning methods typically detect vehicle parts via uniform division, outside tools, or attention modeling. However, such part features often require expensive additional annotations and cause sub-optimal performance in case of unreliable part mask predictions. In this paper, we propose a weakly-supervised Part-Attention Network (PANet) and Part-Mentored Network (PMNet) for Vehicle Re-ID. Firstly, PANet localizes vehicle parts via part-relevant channel recalibration and cluster-based mask generation without vehicle part supervisory information. Secondly, PMNet leverages teacher-student guided learning to distill vehicle part-specific features from PANet and performs multi-scale global-part feature extraction. During inference, PMNet can adaptively extract discriminative part features without part localization by PANet, preventing unstable part mask predictions. We address this Re-ID issue as a multi-task problem and adopt Homoscedastic Uncertainty to learn the optimal weighing of ID losses. Experiments are conducted on two public benchmarks, showing that our approach outperforms recent methods, which require no extra annotations by an average increase of 3.0% in CMC@5 on VehicleID and over 1.4% in mAP on VeRi776. Moreover, our method can extend to the occluded vehicle Re-ID task and exhibits good generalization ability.