# Similarity-based Outlier Detection for Noisy Object Re-Identification Using Beta Mixtures

arXiv: https://arxiv.org/abs/2509.08926 · HTML: https://mlsanity.com/paper/2509.08926/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 51 references that are in the map.
- First posted on arXiv 10 Sep 2025.

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels](https://mlsanity.com/paper/1804.06872/) (2018)
- [Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels](https://mlsanity.com/paper/1805.07836/) (2018)
- [Learning from Noisy Labels with Deep Neural Networks: A Survey](https://mlsanity.com/paper/2007.08199/) (2020)
- [Deep Learning for Person Re-identification: A Survey and Outlook](https://mlsanity.com/paper/2001.04193/) (2020)
- [Symmetric Cross Entropy for Robust Learning with Noisy Labels](https://mlsanity.com/paper/1908.06112/) (2019)
- [Robust Loss Functions under Label Noise for Deep Neural Networks](https://mlsanity.com/paper/1712.09482/) (2017)
- [Meta Pseudo Labels](https://mlsanity.com/paper/2003.10580/) (2020)
- [Multi-Similarity Loss with General Pair Weighting for Deep Metric Learning](https://mlsanity.com/paper/1904.06627/) (2019)
- [Training Deep Neural Networks on Noisy Labels with Bootstrapping](https://mlsanity.com/paper/1412.6596/) (2014)
- [Revisiting Training Strategies and Generalization Performance in Deep Metric Learning](https://mlsanity.com/paper/2002.08473/) (2020)
- [UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learning](https://mlsanity.com/paper/2203.14542/) (2022)
- [Multi-Scale Contrastive Siamese Networks for Self-Supervised Graph Representation Learning](https://mlsanity.com/paper/2105.05682/) (2021)
- [Learning Fast Sample Re-weighting Without Reward Data](https://mlsanity.com/paper/2109.03216/) (2021)
- [GiT: Graph Interactive Transformer for Vehicle Re-identification](https://mlsanity.com/paper/2107.05475/) (2021)
- [Learning to Purify Noisy Labels via Meta Soft Label Corrector](https://mlsanity.com/paper/2008.00627/) (2020)
- [Self-supervised Geometric Features Discovery via Interpretable Attention for Vehicle Re-Identification and Beyond](https://mlsanity.com/paper/2010.09221/) (2020)
- [On Learning Contrastive Representations for Learning with Noisy Labels](https://mlsanity.com/paper/2203.01785/) (2022)
- [Learning from Large-scale Noisy Web Data with Ubiquitous Reweighting for Image Classification](https://mlsanity.com/paper/1811.00700/) (2018)
- [Confidence-guided Centroids for Unsupervised Person Re-Identification](https://mlsanity.com/paper/2211.11921/) (2022)
- [Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection](https://mlsanity.com/paper/2501.11063/) (2025)

## Abstract (arXiv)

Object re-identification (Re-ID) methods are highly sensitive to label noise, which typically leads to significant performance degradation. We address this challenge by reframing Re-ID as a supervised image similarity task and adopting a Siamese network architecture trained to capture discriminative pairwise relationships. Central to our approach is a novel statistical outlier detection (OD) framework, termed Beta-SOD (Beta mixture Similarity-based Outlier Detection), which models the distribution of cosine similarities between embedding pairs using a two-component Beta distribution mixture model. We establish a novel identifiability result for mixtures of two Beta distributions, ensuring that our learning task is well-posed. The proposed OD step complements the Re-ID architecture combining binary cross-entropy, contrastive, and cosine embedding losses that jointly optimize feature-level similarity learning. We demonstrate the effectiveness of Beta-SOD in de-noising and Re-ID tasks for person Re-ID, on CUHK03 and Market-1501 datasets, and vehicle Re-ID, on VeRi-776 dataset. Our method shows superior performance compared to the state-of-the-art methods across various noise levels (10-30%), demonstrating both robustness and broad applicability in noisy Re-ID scenarios. The implementation of Beta-SOD is available at: github.com/waqar3411/Beta-SOD