Delta Lab welcomes you!
Delta Lab, part of the School of Computer and Software at Hohai University, China, is dedicated to advancing the field of computer vision. Our research focuses on several cutting-edge areas:
- Computer Vision: We specialize in few-shot learning for image segmentation and end-to-end text detection and recognition.
- Artificial Intelligence: Our work includes explainable AI and causal reasoning, aiming to make AI systems more transparent and understandable.
- Multimedia Computing: We explore medical image analysis, image encryption, and super-resolution methods to enhance multimedia data processing.
- Intelligent Water Conservancy: We apply artificial intelligence techniques to process hydrology big data, supporting advancements in water resource management.
At Delta Lab, we are committed to pushing the boundaries of technology through both theoretical research and practical applications. If you are passionate about computer vision and its applications, we invite you to join us. For more information about our research or to get involved, please contact us at wuyirui@hhu.edu.cn. We look forward to collaborating with you.
Latest News
WeChat Official Account When the amount of data is small, the performance of deep learning will be greatly limited. Few-shot learning aims to use prior knowledge to quickly draw conclusions in limited new tasks, thus significantly narrowing the gap between artificial intelligence and humans. Centering around the theory of few-shot learning and focusing on knowledge representation methods as well as the embedding of knowledge in neural networks, we have studied the algorithm designs such as superclass representation, graph network models, knowledge reasoning, and zero-shot classification guided by CLIP. These efforts are aimed at alleviating common issues like catastrophic forgetting and feature drift during the process of incremental few-shot learning, and solving classic visual problems such as image semantic segmentation and image classification in the context of few-shot scenarios.