# Part-dependent Label Noise: Towards Instance-dependent Label Noise

arXiv: https://arxiv.org/abs/2006.07836 · HTML: https://mlsanity.com/paper/2006.07836/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jun 2020.

## Built on by (most cited first, 30 of 40)

- [Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations](https://mlsanity.com/paper/2110.12088/) (2021)
- [Understanding and Improving Early Stopping for Learning with Noisy Labels](https://mlsanity.com/paper/2106.15853/) (2021)
- [Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels](https://mlsanity.com/paper/2102.05291/) (2021)
- [Open-set Label Noise Can Improve Robustness Against Inherent Label Noise](https://mlsanity.com/paper/2106.10891/) (2021)
- [NGC: A Unified Framework for Learning with Open-World Noisy Data](https://mlsanity.com/paper/2108.11035/) (2021)
- [Understanding Robust Overfitting of Adversarial Training and Beyond](https://mlsanity.com/paper/2206.08675/) (2022)
- [Instance-dependent Label-noise Learning under a Structural Causal Model](https://mlsanity.com/paper/2109.02986/) (2021)
- [When Source-Free Domain Adaptation Meets Learning with Noisy Labels](https://mlsanity.com/paper/2301.13381/) (2023)
- [Towards Understanding Deep Learning from Noisy Labels with Small-Loss Criterion](https://mlsanity.com/paper/2106.09291/) (2021)
- [Identifiability of Label Noise Transition Matrix](https://mlsanity.com/paper/2202.02016/) (2022)
- [Self-Filtering: A Noise-Aware Sample Selection for Label Noise with Confidence Penalization](https://mlsanity.com/paper/2208.11351/) (2022)
- [Meta Discovery: Learning to Discover Novel Classes given Very Limited Data](https://mlsanity.com/paper/2102.04002/) (2021)
- [Estimating Instance-dependent Bayes-label Transition Matrix using a Deep Neural Network](https://mlsanity.com/paper/2105.13001/) (2021)
- [Robust Generalization against Photon-Limited Corruptions via Worst-Case Sharpness Minimization](https://mlsanity.com/paper/2303.13087/) (2023)
- [Progressive Purification for Instance-Dependent Partial Label Learning](https://mlsanity.com/paper/2206.00830/) (2022)
- [Understanding Instance-Level Label Noise: Disparate Impacts and Treatments](https://mlsanity.com/paper/2102.05336/) (2021)
- [Adaptive Sample Selection for Robust Learning under Label Noise](https://mlsanity.com/paper/2106.15292/) (2021)
- [Learning with Noisy Labels by Efficient Transition Matrix Estimation to Combat Label Miscorrection](https://mlsanity.com/paper/2111.14932/) (2021)
- [Removing Adversarial Noise in Class Activation Feature Space](https://mlsanity.com/paper/2104.09197/) (2021)
- [Instance-Dependent Noisy Label Learning via Graphical Modelling](https://mlsanity.com/paper/2209.00906/) (2022)
- [Centrality and Consistency: Two-Stage Clean Samples Identification for Learning with Instance-Dependent Noisy Labels](https://mlsanity.com/paper/2207.14476/) (2022)
- [Analysing the Noise Model Error for Realistic Noisy Label Data](https://mlsanity.com/paper/2101.09763/) (2021)
- [Tackling Instance-Dependent Label Noise via a Universal Probabilistic Model](https://mlsanity.com/paper/2101.05467/) (2021)
- [Learning to Rectify for Robust Learning with Noisy Labels](https://mlsanity.com/paper/2111.04239/) (2021)
- [Model Generalization on COVID-19 Fake News Detection](https://mlsanity.com/paper/2101.03841/) (2021)
- [On the Robustness of Monte Carlo Dropout Trained with Noisy Labels](https://mlsanity.com/paper/2103.12002/) (2021)
- [Counterfactual Prediction Under Outcome Measurement Error](https://mlsanity.com/paper/2302.11121/) (2023)
- [Bootstrapping the Relationship Between Images and Their Clean and Noisy Labels](https://mlsanity.com/paper/2210.08826/) (2022)
- [Learning with Group Noise](https://mlsanity.com/paper/2103.09468/) (2021)
- [Confidence Adaptive Regularization for Deep Learning with Noisy Labels](https://mlsanity.com/paper/2108.08212/) (2021)

## Abstract (arXiv)

Learning with the textitinstance-dependent label noise is challenging, because it is hard to model such real-world noise. Note that there are psychological and physiological evidences showing that we humans perceive instances by decomposing them into parts. Annotators are therefore more likely to annotate instances based on the parts rather than the whole instances, where a wrong mapping from parts to classes may cause the instance-dependent label noise. Motivated by this human cognition, in this paper, we approximate the instance-dependent label noise by exploiting textitpart-dependent label noise. Specifically, since instances can be approximately reconstructed by a combination of parts, we approximate the instance-dependent textittransition matrix for an instance by a combination of the transition matrices for the parts of the instance. The transition matrices for parts can be learned by exploiting anchor points (i.e., data points that belong to a specific class almost surely). Empirical evaluations on synthetic and real-world datasets demonstrate our method is superior to the state-of-the-art approaches for learning from the instance-dependent label noise.