Countering Noisy Labels By Learning From Auxiliary Clean Labels
We consider the learning from noisy labels (NL) problem which emerges in many real-world applications. In addition to the widely-studied synthetic noise in the NL literature, we also consider the pseudo labels in semi-supervised learning (Semi-SL) as a special case of NL. For both types of noise, we argue that the generalization performance of existing methods is highly coupled with the quality of noisy labels. Therefore, we counter the problem from a novel and unified perspective: learning from the auxiliary clean labels. Specifically, we propose the Rotational-Decoupling Consistency Regularization (RDCR) framework that integrates the consistency-based methods with the self-supervised rotation task to learn noise-tolerant representations. The experiments show that RDCR achieves comparable or superior performance than the state-of-the-art methods under small noise, while outperforms the existing methods significantly when there is large noise.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Learning with Noisy Labels over Imbalanced Subpopulations
Learning with Noisy Labels (LNL) has attracted significant attention from the research community. Many recent LNL methods rely on the assumption that clean samples tend to have "small loss". However, this assumption alwa…
Learning with noisy labelsSelf-refining of Pseudo Labels for Music Source Separation with Noisy Labeled Data
Music source separation (MSS) faces challenges due to the limited availability of correctly-labeled individual instrument tracks. With the push to acquire larger datasets to improve MSS performance, the inevitability of …
Instrument RecognitionMusic Source SeparationRobust Curriculum Learning: from clean label detection to noisy label self-correction
Neural nets training can easily overfit to noisy labels and end with poor generalization performance. Existing methods address this problem by (1) filtering out the noisy data and only using the clean data for training o…
Probabilistic End-to-end Noise Correction for Learning with Noisy Labels
Deep learning has achieved excellent performance in various computer vision tasks, but requires a lot of training examples with clean labels. It is easy to collect a dataset with noisy labels, but such noise makes networ…
Image ClassificationLearning with noisy labelsToward Robustness against Label Noise in Training Deep Discriminative Neural Networks
Collecting large training datasets, annotated with high-quality labels, is costly and time-consuming. This paper proposes a novel framework for training deep convolutional neural networks from noisy labeled datasets that…