Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels
This addresses the challenge of noisy label correction in machine learning, offering a more efficient alternative to anchor-based methods, though it appears incremental as it builds on existing transition matrix estimation approaches.
The paper tackles the problem of estimating the label noise transition matrix in learning with noisy labels by proposing a method based on clusterability instead of relying on anchor points, achieving improved sample complexity and demonstrating accuracy on synthetic and real-world datasets like CIFAR-10/100 and Clothing1M.
The label noise transition matrix, characterizing the probabilities of a training instance being wrongly annotated, is crucial to designing popular solutions to learning with noisy labels. Existing works heavily rely on finding "anchor points" or their approximates, defined as instances belonging to a particular class almost surely. Nonetheless, finding anchor points remains a non-trivial task, and the estimation accuracy is also often throttled by the number of available anchor points. In this paper, we propose an alternative option to the above task. Our main contribution is the discovery of an efficient estimation procedure based on a clusterability condition. We prove that with clusterable representations of features, using up to third-order consensuses of noisy labels among neighbor representations is sufficient to estimate a unique transition matrix. Compared with methods using anchor points, our approach uses substantially more instances and benefits from a much better sample complexity. We demonstrate the estimation accuracy and advantages of our estimates using both synthetic noisy labels (on CIFAR-10/100) and real human-level noisy labels (on Clothing1M and our self-collected human-annotated CIFAR-10). Our code and human-level noisy CIFAR-10 labels are available at https://github.com/UCSC-REAL/HOC.