Abstract Machine learning methods strive to acquire a robust model during the training
process that can effectively generalize to test samples, even in the presence of distribution …

Research in the medical imaging field using deep learning approaches has become
progressively contingent. Scientific findings reveal that supervised deep learning methods' …

Over the last decade, neural networks have reached almost every field of science and
become a crucial part of various real world applications. Due to the increasing spread …

Existing long-tailed recognition methods, aiming to train class-balanced models from long-
tailed data, generally assume the models would be evaluated on the uniform test class …

Both Minsky's" society of mind" and Schmidhuber's" learning to think" inspire diverse
societies of large multimodal neural networks (NNs) that solve problems by interviewing …

Abstract Test-time augmentation---the aggregation of predictions across transformed
versions of a test input---is a common practice in image classification. Traditionally …

Recent studies have shown that graph neural networks (GNNs) exhibit strong biases
towards the node degree: they usually perform satisfactorily on high-degree nodes with rich …

The elucidation of transition state (TS) structures is essential for understanding the
mechanisms of chemical reactions and exploring reaction networks. Despite significant …

We propose a new and effective self-distillation framework with our new Test-Time
Augmentation (TTA) and Transformer based Voxel Feature Encoder (TransVFE) for robust …

Most of the existing salient object detection (SOD) models focus on improving the overall
model performance, without explicitly explaining the discrepancy between the training and …