TL;DR
Robust loss functions to support adaptation to noisy labels are developed by improving the cross-entropy loss function, which is effective with clean data but lacks robustness with noisy labels.
This work conducts a comparative empirical study of five MU methods across symmetric, asymmetric, instance-dependent, and open-set noise on CIFAR-10, CIFAR-100, and the real-world noisy dataset Food-101N and finds that the appropriate unlearning strategy is conditioned on the noise structure.
Training state-of-the-art models increasingly requires learning from large, heterogeneous datasets whose examples vary in quality, domain relevance, and source of supervision. Dataweighting---assigning different weights to training examples---offers a general way to control how such data influences training, but learni...
Deep neural networks (DNNs), due to their over-parameterization and memorization capacity, are prone to fitting incorrect labels in training data, which can substantially degrade their performance. Consequently, LNL has attracted increasing attention. Popular LNL methods select potentially clean samples for reliable su...
Wave-BLS, a robust broad learning framework that integrates the wave loss function, which is asymmetric, bounded, and smooth, enabling controlled penalization of large errors, is proposed, establishing Wave-BLS as a stable and robust alternative to existing broad learning models for learning under data uncertainty.
This paper tackles visible challenges in deep ensemble learning, where deep neural networks serve as ensemble members: training and storage burdens, and robustness of cautious (set-valued) predictions targeting multiple utilities, which may involve reward-sensitivity. To mitigate the training and storage burdens, we pr...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
