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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ahmad, Waqar, Murphy, Evan, Krylov, Vladimir A.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914037822914560
author Ahmad, Waqar
Murphy, Evan
Krylov, Vladimir A.
author_facet Ahmad, Waqar
Murphy, Evan
Krylov, Vladimir A.
contents 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
format Preprint
id arxiv_https___arxiv_org_abs_2509_08926
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Similarity-based Outlier Detection for Noisy Object Re-Identification Using Beta Mixtures
Ahmad, Waqar
Murphy, Evan
Krylov, Vladimir A.
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Statistics Theory
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
title Similarity-based Outlier Detection for Noisy Object Re-Identification Using Beta Mixtures
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Statistics Theory
url https://arxiv.org/abs/2509.08926