AI alignment aims to make AI systems behave in line with human intentions and values. As
AI systems grow more capable, the potential large-scale risks associated with misaligned AI …

Oriented object detection is a practical and challenging task in remote sensing image
interpretation. Nowadays, oriented detectors mostly use horizontal boxes as intermedium to …

Following the widespread use of deep learning for genomics, deep generative modeling is
also becoming a viable methodology for the broad field. Deep generative models (DGMs) …

Saliency-based representation visualization (SRV)($ eg $, Grad-CAM) is one of the most
classical and widely adopted explainable artificial intelligence (XAI) methods for its simplicity …

Abstract The Generative Adversarial Network (GAN) is commonly used for medical image
augmentation, a method to alleviate the data shortage for downstream tasks. However …

Weakly supervised object detection (WSOD) in remote sensing images remains a
challenging task when learning object detectors with only image-level labels. As we know …

This study evaluated the performance of generative adversarial network (GAN)-synthesized
periapical images for classifying C-shaped root canals, which are challenging to diagnose …

Vehicle re-identification aims to identify vehicles from different cameras and has drawn
much attention in the multimedia community. In recent years, significant achievements in …

Global covariance pooling (GCP) as an effective alternative to global average pooling has
shown good capacity to improve deep convolutional neural networks (CNNs) in a variety of …

Thyroid-associated ophthalmopathy (TAO) is an organ-specific autoimmune disease that
seriously affects patient's life and health. However, the early diagnosis of TAO is highly …