mlsanityData to 14 Oct 2026

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

arXiv 2509.08926 ↗First posted 10 Sep 2025cs.CV cs.AI cs.LGcited by 0

Not on the map. Why?

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

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

24 of 51 references.

References · 24

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  4. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,849
  5. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,059
  6. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 997
  7. 2020Learning from Noisy Labels with Deep Neural Networks: A Surveycited by 582
  8. 2020Deep Learning for Person Re-identification: A Survey and Outlookcited by 549
  9. 2019Symmetric Cross Entropy for Robust Learning with Noisy Labelscited by 500
  10. 2017Robust Loss Functions under Label Noise for Deep Neural Networkscited by 443
  11. 2020Meta Pseudo Labelscited by 374
  12. 2019Multi-Similarity Loss with General Pair Weighting for Deep Metric Learningcited by 368
12 more
  1. 2014Training Deep Neural Networks on Noisy Labels with Bootstrappingcited by 322
  2. 2020Revisiting Training Strategies and Generalization Performance in Deep Metric Learningcited by 100
  3. 2022UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learningcited by 77
  4. 2021Multi-Scale Contrastive Siamese Networks for Self-Supervised Graph Representation Learningcited by 70
  5. 2021Learning Fast Sample Re-weighting Without Reward Datacited by 69
  6. 2021GiT: Graph Interactive Transformer for Vehicle Re-identificationcited by 49
  7. 2020Learning to Purify Noisy Labels via Meta Soft Label Correctorcited by 39
  8. 2020Self-supervised Geometric Features Discovery via Interpretable Attention for Vehicle Re-Identification and Beyondcited by 25
  9. 2022On Learning Contrastive Representations for Learning with Noisy Labelscited by 21
  10. 2018Learning from Large-scale Noisy Web Data with Ubiquitous Reweighting for Image Classificationcited by 7
  11. 2022Confidence-guided Centroids for Unsupervised Person Re-Identificationcited by 2
  12. 2025Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selectioncited by 1

Built on by

Not cited yet.