AI is undergoing a paradigm shift with the rise of models (eg, BERT, DALL-E, GPT-3) that are trained on broad data at scale and are adaptable to a wide range of downstream tasks. We …
Fine-grained image analysis (FGIA) is a longstanding and fundamental problem in computer vision and pattern recognition, and underpins a diverse set of real-world applications. The …
Self-supervised learning (SSL) is a scalable way to learn general visual representations since it learns without labels. However, large-scale unlabeled datasets in the wild often have …
Machine learning systems deployed in the wild are often trained on a source distribution but deployed on a different target distribution. Unlabeled data can be a powerful point of …
Y Wang, NAA Braham, Z Xiong, C Liu… - … and Remote Sensing …, 2023 - ieeexplore.ieee.org
Self-supervised pretraining bears the potential to generate expressive representations from large-scale Earth observation (EO) data without human annotation. However, most existing …
Images of the natural world collected by a variety of cameras from drones to individual phones are increasingly abundant sources of biological information. There is an explosion …
Abstract Vision Transformers (ViTs) have gained significant popularity in recent years and have proliferated into many applications. However, their behavior under different learning …
J Zhang, L Gao, B Hao, H Huang… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Out-of-distribution (OOD) detection aims to detect “unknown” data whose labels have not been seen during the in-distribution (ID) training process. Recent progress in representation …
Empowered by large datasets, eg, ImageNet and MS COCO, unsupervised learning on large-scale data has enabled significant advances for classification tasks. However, whether …