A5007542723- Advanced Neural Network Applications
- Advanced Image and Video Retrieval Techniques
- Privacy-Preserving Technologies in Data
- Multimodal Machine Learning Applications
- Advanced Graph Neural Networks
- Remote-Sensing Image Classification
- Domain Adaptation and Few-Shot Learning
- Recommender Systems and Techniques
University of Electronic Science and Technology of China
2023
Remote sensing object detection is a basic yet challenging task in remote image understanding. In contrast to horizontal objects, objects are commonly densely packed with arbitrary orientations and highly complex backgrounds. Existing methods lack an effective mechanism exploit these characteristics distinguish various targets. Unlike mainstream approaches ignoring spatial interaction among targets, this paper proposes shape-adaptive repulsion constraint on point representation capture...
As a self-supervised learning method, the graph contrastive achieve admirable performance in pre-training tasks, and can be fine-tuned for multiple downstream tasks such as protein structure prediction, social recommendation, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">etc.</i> One prerequisite is support of huge graphs training procedure. However, data nowadays are distributed various devices hold by different owners, like those smart...