Learning to Detect Noisy Labels Using Model-Based Features
Label noise is ubiquitous in various machine learning scenarios such as self-labeling with model predictions and erroneous data annotation. Many existing approaches are based on heuristics such as sample losses, which might not be flexible enough to achieve optimal solutions. Meta learning based methods address this issue by learning a data selection function, but can be hard to optimize. In light of these pros and cons, we propose Selection-Enhanced Noisy label Training (SENT) that does not rely on meta learning while having the flexibility of being data-driven. SENT transfers the noise distribution to a clean set and trains a model to distinguish noisy labels from clean ones using model-based features. Empirically, on a wide range of tasks including text classification and speech recognition, SENT improves performance over strong baselines under the settings of self-training and label corruption.
Code (1)
Tasks
Meta-Learningspeech-recognitionSpeech Recognitiontext-classificationText ClassificationSimilar Papers 제목 키워드 기반
ADMoE: Anomaly Detection with Mixture-of-Experts from Noisy Labels
Existing works on anomaly detection (AD) rely on clean labels from human annotators that are expensive to acquire in practice. In this work, we propose a method to leverage weak/noisy labels (e.g., risk scores generated …
Anomaly DetectionMixture-of-ExpertsIterative Learning with Open-set Noisy Labels
Large-scale datasets possessing clean label annotations are crucial for training Convolutional Neural Networks (CNNs). However, labeling large-scale data can be very costly and error-prone, and even high-quality datasets…
Incomplete Multi-View Weak-Label Learning with Noisy Features and Imbalanced Labels
A variety of modern applications exhibit multi-view multi-label learning, where each sample has multi-view features, and multiple labels are correlated via common views. Current methods usually fail to directly deal with…
Multi-Label LearningScalable Penalized Regression for Noise Detection in Learning with Noisy Labels
Noisy training set usually leads to the degradation of generalization and robustness of neural networks. In this paper, we propose using a theoretically guaranteed noisy label detection framework to detect and remove noi…
Image ClassificationLearning with noisy labelsregressionA Data-Centric Framework for Detecting and Correcting Corrupted Labels
The performance of machine learning and deep learning models largely depends on the quality of the training data. However, the quality of the real-world datasets is often compromised by noisy labels, which can substantia…