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

Abstract

Learning with the \textit{instance-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 \textit{part-dependent} label noise. Specifically, since instances can be approximately reconstructed by a combination of parts, we approximate the instance-dependent \textit{transition 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.

Cited by in corpus (26)

• Active label cleaning for improved dataset quality under resource constraints
• Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learning
• Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations
• Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Rates
• Low-Quality Training Data Only? A Robust Framework for Detecting Encrypted Malicious Network Traffic
• Provably Consistent Partial-Label Learning
• Provably End-to-end Label-Noise Learning without Anchor Points
• Learning Noise Transition Matrix from Only Noisy Labels via Total Variation Regularization
• Extended T: Learning with Mixed Closed-set and Open-set Noisy Labels
• Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels
• Beyond Class-Conditional Assumption: A Primary Attempt to Combat Instance-Dependent Label Noise
• A Second-Order Approach to Learning with Instance-Dependent Label Noise
• Rethinking Importance Weighting for Deep Learning under Distribution Shift
• DyGen: Learning from Noisy Labels via Dynamics-Enhanced Generative Modeling
• Counterfactual Prediction Under Outcome Measurement Error
• Robustness of Accuracy Metric and its Inspirations in Learning with Noisy Labels
• Adaptive Sample Selection for Robust Learning under Label Noise
• Toward Fair Graph Neural Networks Via Dual-Teacher Knowledge Distillation
• Learning with Noisy Labels by Efficient Transition Matrix Estimation to Combat Label Miscorrection
• NGC: A Unified Framework for Learning with Open-World Noisy Data
• Rethinking Noisy Label Models: Labeler-Dependent Noise with Adversarial Awareness
• Instance-dependent Noisy-label Learning with Graphical Model Based Noise-rate Estimation
• Combating Label Noise With A General Surrogate Model For Sample Selection
• Binary Classification from Multiple Unlabeled Datasets via Surrogate Set Classification
• Learning to Rectify for Robust Learning with Noisy Labels
• Meta Label Correction for Noisy Label Learning