Robust Person Re-Identification by Modelling Feature Uncertainty

By Tianyuan Yu, Da Li, Yongxin Yang, Timothy M. Hospedales, Tao A. Xiang. 2019

152 citations recorded by the source corpus.

We aim to learn deep person re-identification (ReID) models that are robust against noisy training data. Two types of noise are prevalent in practice: (1) label noise caused by human annotator errors and (2) data outliers caused by person detector errors or occlusion. Both types of noise pose serious problems for training ReID models, yet have been largely ignored so far. In this paper, we propose a novel deep network termed DistributionNet for robust ReID. Instead of representing each person image as a feature vector, DistributionNet models it as a Gaussian distribution with its variance representing the uncertainty of the extracted features. A carefully designed loss is formulated in DistributionNet to unevenly allocate uncertainty across training samples. Consequently, noisy samples are assigned large variance/uncertainty, which effectively alleviates their negative impacts on model fitting. Extensive experiments demonstrate that our model is more effective than alternative noise-robust deep models. The source code is available at: https://github.com/TianyuanYu/DistributionNet

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

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

In Biomedical Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

S3C: Self-Supervised Stochastic Classifiers for Few-Shot Class-Incremental Learning (2023, methodology): “Recently, it has been used for person re-identification [42] and unsupervised domain adaptation [24] tasks.”
Deep Learning for Person Re-Identification: A Survey and Outlook (2020, methodology): “A Distribution Net (DNet) that models the feature uncertainty is proposed in [228] for robust Re-ID model learning against label noise, reducing the impact of samples with high feature uncertainty.”
Data Uncertainty Learning in Face Recognition (2020, background): “, semantic segmentation [19, 21], object detection [6, 25] and person Re-ID [50], have introduced deep uncertainty learning to CNNs for the improvement of model robustness and interpretability.”
Stochastic Classifiers for Unsupervised Domain Adaptation (2020, background): “For example, [50] proposed an uncertainty aware multi-modal BNNs for activity recognition and [59] modelled the feature uncertainty using distributions in person re-identification.”
A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges (2020, background): “[10], optical flow estimation and motion prediction [249], [410], [411], human pose estimation and pedestrian localization [412], [413], [305], person re-identification and face recognition [414], [415], [416], camera re-localization [397], avoiding adversarial attacks [417], [418], during the years”
Uncertainty-Aware Learning for Zero-Shot Semantic Segmentation (2020, methodology): “Besides serving as prediction conﬁdence as in the above methods, uncertainty is also modeled in distributional feature representation for applications like person ReID [58] and facial recognition [5, 49] to achieve robust feature learning.”
Prime-Aware Adaptive Distillation (2020, background): “, face recognition [30], semantic segmentation [15,16], object detection [7,17] and person re-identification(re-ID) [38].”
Uncertainty-Guided Transformer Reasoning for Camouflaged Object Detection (2021, methodology): “These techniques have been successfully applied to modeling uncertainty for semantic segmentation / scene parsing [19, 23], person reidentification [56] and medical image analysis [28].”
Embracing Uncertainty: Decoupling and De-bias for Robust Temporal Grounding (2021, background): “From a probabilistic perspective, it means that the feature is regarded as a random variable to model uncertainty [42].”