Neural networks trained on distilled data often produce over-confident output and require
correction by calibration methods. Existing calibration methods such as temperature scaling …

Dataset distillation aims to minimize the time and memory needed for training deep networks
on large datasets, by creating a small set of synthetic images that has a similar …

Miscalibration--a mismatch between a model's confidence and its correctness--of Deep
Neural Networks (DNNs) makes their predictions hard to rely on. Ideally, we want networks …

Deep neural networks with millions of parameters may suffer from poor generalization due to
overfitting. To mitigate the issue, we propose a new regularization method that penalizes the …

Dataset distillation is the task of synthesizing a small dataset such that a model trained on
the synthetic set will match the test accuracy of the model trained on the full dataset. In this …

Data-free learning for student networks is a new paradigm for solving users' anxiety caused
by the privacy problem of using original training data. Since the architectures of modern …

Researchers have long tried to minimize training costs in deep learning while maintaining
strong generalization across diverse datasets. Emerging research on dataset distillation …

Recent studies have revealed that, beyond conventional accuracy, calibration should also
be considered for training modern deep neural networks. To address miscalibration during …

Dataset distillation aims to synthesize small datasets with little information loss from original
large-scale ones for reducing storage and training costs. Recent state-of-the-art methods …

Contemporary machine learning which involves training large neural networks on massive
datasets faces significant computational challenges. Dataset distillation as a recent …