Recently, learning with soft labels has been shown to achieve better performance than
learning with hard labels in terms of model generalization, calibration, and robustness …

Classification is a fundamental task in science and engineering on which machine learning
methods have shown outstanding performances. However, it is challenging to determine …

Adversarial examples pose a security threat to many critical systems built on neural
networks. While certified training improves robustness, it also decreases accuracy …

Among the flourishing research of weakly supervised learning (WSL), we recognize the lack
of a unified interpretation of the mechanism behind the weakly supervised scenarios, let …

Research has shown that deep networks tend to be overly optimistic about their predictions,
leading to an underestimation of prediction errors. Due to the limited nature of data, existing …

Adversarial examples pose a security threat to many critical systems built on neural
networks. Given that deterministic robustness often comes with significantly reduced …

Classification is a fundamental task in many applications on which data-driven methods
have shown outstanding performances. However, it is challenging to determine whether …

Advances in AI for health applications rely on evaluating performance against labeled test
data. In the area of mental health, self-report labels from surveys such as the Patient Health …

As a heuristic for improving test accuracy in classification, the" flooding" method proposed by
Ishida et al.(2020) sets a threshold for the average surrogate loss at training time; above the …