# Noise-resistant Deep Metric Learning with Ranking-based Instance Selection

arXiv: https://arxiv.org/abs/2103.16047 · HTML: https://mlsanity.com/paper/2103.16047/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 59 references that are in the map.
- First posted on arXiv 30 Mar 2021.

## Builds on (most cited first, 30 of 42)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [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)
- [In Defense of the Triplet Loss for Person Re-Identification](https://mlsanity.com/paper/1703.07737/) (2017)
- [Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach](https://mlsanity.com/paper/1609.03683/) (2016)
- [MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels](https://mlsanity.com/paper/1712.05055/) (2017)
- [End-to-End Learning of Visual Representations from Uncurated Instructional Videos](https://mlsanity.com/paper/1912.06430/) (2019)
- [Deep Metric Learning via Lifted Structured Feature Embedding](https://mlsanity.com/paper/1511.06452/) (2015)
- [Circle Loss: A Unified Perspective of Pair Similarity Optimization](https://mlsanity.com/paper/2002.10857/) (2020)
- [How does Disagreement Help Generalization against Label Corruption?](https://mlsanity.com/paper/1901.04215/) (2019)
- [Multi-Similarity Loss with General Pair Weighting for Deep Metric Learning](https://mlsanity.com/paper/1904.06627/) (2019)
- [A Metric Learning Reality Check](https://mlsanity.com/paper/2003.08505/) (2020)
- [Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrieval](https://mlsanity.com/paper/2004.01804/) (2020)
- [Combating noisy labels by agreement: A joint training method with co-regularization](https://mlsanity.com/paper/2003.02752/) (2020)
- [Sampling Matters in Deep Embedding Learning](https://mlsanity.com/paper/1706.07567/) (2017)
- [No Fuss Distance Metric Learning using Proxies](https://mlsanity.com/paper/1703.07464/) (2017)
- [Proxy Anchor Loss for Deep Metric Learning](https://mlsanity.com/paper/2003.13911/) (2020)
- [Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking](https://mlsanity.com/paper/1803.11285/) (2018)
- [Learning with Average Precision: Training Image Retrieval with a Listwise Loss](https://mlsanity.com/paper/1906.07589/) (2019)
- [CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noise](https://mlsanity.com/paper/1711.07131/) (2017)
- [SoftTriple Loss: Deep Metric Learning Without Triplet Sampling](https://mlsanity.com/paper/1909.05235/) (2019)
- [Learning to Learn from Noisy Labeled Data](https://mlsanity.com/paper/1812.05214/) (2018)
- [Cross-Batch Memory for Embedding Learning](https://mlsanity.com/paper/1912.06798/) (2019)
- [End-to-end Learning of Deep Visual Representations for Image Retrieval](https://mlsanity.com/paper/1610.07940/) (2016)
- [Learning with Symmetric Label Noise: The Importance of Being Unhinged](https://mlsanity.com/paper/1505.07634/) (2015)
- [Iterative Learning with Open-set Noisy Labels](https://mlsanity.com/paper/1804.00092/) (2018)
- [Meta Label Correction for Noisy Label Learning](https://mlsanity.com/paper/1911.03809/) (2019)
- [ProxyNCA++: Revisiting and Revitalizing Proxy Neighborhood Component Analysis](https://mlsanity.com/paper/2004.01113/) (2020)

## Built on by (most cited first, 23 of 23)

- [UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learning](https://mlsanity.com/paper/2203.14542/) (2022)
- [Instance-Dependent Label-Noise Learning with Manifold-Regularized Transition Matrix Estimation](https://mlsanity.com/paper/2206.02791/) (2022)
- [Towards Graph Contrastive Learning: A Survey and Beyond](https://mlsanity.com/paper/2405.11868/) (2024)
- [Enhancing Vision-Language Compositional Understanding with Multimodal Synthetic Data](https://mlsanity.com/paper/2503.01167/) (2025)
- [Learning with Label Noise for Image Retrieval by Selecting Interactions](https://mlsanity.com/paper/2112.10453/) (2021)
- [RankDNN: Learning to Rank for Few-shot Learning](https://mlsanity.com/paper/2211.15320/) (2022)
- [A Survey of Computer Vision Technologies In Urban and Controlled-environment Agriculture](https://mlsanity.com/paper/2210.11318/) (2022)
- [Center Contrastive Loss for Metric Learning](https://mlsanity.com/paper/2308.00458/) (2023)
- [Deep Metric Learning with Chance Constraints](https://mlsanity.com/paper/2209.09060/) (2022)
- [A Survey of Historical Learning: Learning Models with Learning History](https://mlsanity.com/paper/2303.12992/) (2023)
- [Deep Image Retrieval is not Robust to Label Noise](https://mlsanity.com/paper/2205.11195/) (2022)
- [ProcSim: Proxy-based Confidence for Robust Similarity Learning](https://mlsanity.com/paper/2311.00668/) (2023)
- [Towards certifiable AI in aviation: landscape, challenges, and opportunities](https://mlsanity.com/paper/2409.08666/) (2024)
- [Noise-Aware Generalization: Robustness to In-Domain Noise and Out-of-Domain Generalization](https://mlsanity.com/paper/2504.02996/) (2025)
- [Robust Calibrate Proxy Loss for Deep Metric Learning](https://mlsanity.com/paper/2304.09162/) (2023)
- [Generalized Sum Pooling for Metric Learning](https://mlsanity.com/paper/2308.09228/) (2023)
- [Transformer-empowered Multi-modal Item Embedding for Enhanced Image Search in E-Commerce](https://mlsanity.com/paper/2311.17954/) (2023)
- [Angel or Devil: Discriminating Hard Samples and Anomaly Contaminations for Unsupervised Time Series Anomaly Detection](https://mlsanity.com/paper/2410.21322/) (2024)
- [Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection](https://mlsanity.com/paper/2501.11063/) (2025)
- [Noise-Resistant Deep Metric Learning with Probabilistic Instance Filtering](https://mlsanity.com/paper/2108.01431/) (2021)
- [LIGAR: Lightweight General-purpose Action Recognition](https://mlsanity.com/paper/2108.13153/) (2021)
- [Debiased Orthogonal Boundary-Driven Efficient Noise Mitigation](https://mlsanity.com/paper/2410.01944/) (2024)
- [SynMulti: Synthetic-to-Real Learning for Multimodal Video Understanding](https://mlsanity.com/paper/2604.12335/) (2026)

## Abstract (arXiv)

The existence of noisy labels in real-world data negatively impacts the performance of deep learning models. Although much research effort has been devoted to improving robustness to noisy labels in classification tasks, the problem of noisy labels in deep metric learning (DML) remains open. In this paper, we propose a noise-resistant training technique for DML, which we name Probabilistic Ranking-based Instance Selection with Memory (PRISM). PRISM identifies noisy data in a minibatch using average similarity against image features extracted by several previous versions of the neural network. These features are stored in and retrieved from a memory bank. To alleviate the high computational cost brought by the memory bank, we introduce an acceleration method that replaces individual data points with the class centers. In extensive comparisons with 12 existing approaches under both synthetic and real-world label noise, PRISM demonstrates superior performance of up to 6.06% in Precision@1.