Y Zou, S Zhang, Y Li, R Li - Advances in neural information …, 2022 - proceedings.neurips.cc
Few-shot class-incremental learning (FSCIL) is designed to incrementally recognize novel classes with only few training samples after the (pre-) training on base classes with sufficient …
B Zhang, S Feng, X Li, Y Ye, R Ye… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Few-shot remote sensing scene classification (FSRSSC) is an important task, which aims to recognize novel scene classes with few examples. Recently, several studies attempt to …
Comprehensive 3D scene understanding, both geometrically and semantically, is important for real-world applications such as robot perception. Most of the existing work has focused …
J Zhang, X Zhang, Z Wang - … on Circuits and Systems for Video …, 2022 - ieeexplore.ieee.org
Few-shot learning is an extremely challenging task in computer vision that has attracted increased research attention in recent years. However, most recent methods do not fully use …
S Zheng, Z Bao, M Hebert… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Multi-task visual learning is a critical aspect of computer vision. Current research, however, predominantly concentrates on the multi-task dense prediction setting, which overlooks the …
Few-shot learning, which aims to learn the concept of novel category from extremely limited labeled samples, has received intense interests in remote sensing image scene …
Z Bao, M Hebert, YX Wang - International Conference on …, 2022 - proceedings.mlr.press
Generative modeling has recently shown great promise in computer vision, but it has mostly focused on synthesizing visually realistic images. In this paper, motivated by multi-task …
Background Natural language processing (NLP) has become an emerging technology in health care that leverages a large amount of free-text data in electronic health records to …
Abstract Representation learning models employing Siamese structures have consistently demonstrated exceptional performance across various fields, including deep learning …