Motivated by the gap between theoretical optimal approximation rates of deep neural networks (DNNs) and the accuracy realized in practice, we seek to improve the training of …
M Zhai, L Chen, G Mori - … of the IEEE/CVF Conference on …, 2021 - openaccess.thecvf.com
Deep neural networks are susceptible to catastrophic forgetting: when encountering a new task, they can only remember the new task and fail to preserve its ability to accomplish …
While deep learning has resulted in major breakthroughs in many application domains, the frameworks commonly used in deep learning remain fragile to artificially-crafted and …
Continual learning has been widely studied in recent years to resolve the catastrophic forgetting of deep neural networks. In this paper, we first enforce a low-rank filter subspace …
W Chen, Z Miao, Q Qiu - Advances in Neural Information …, 2024 - proceedings.neurips.cc
Analyzing representational similarity among neural networks (NNs) is essential for interpreting or transferring deep models. In application scenarios where numerous NN …
Z Wang, Z Miao, J Hu, Q Qiu - Proceedings of the IEEE/CVF …, 2021 - openaccess.thecvf.com
Applying feature dependent network weights have been proved to be effective in many fields. However, in practice, restricted by the enormous size of model parameters and …
The critical challenge of single image inpainting stems from accurate semantic inference via limited information while maintaining image quality. Typical methods for semantic image …
T Cortinhal, F Kurnaz, EE Aksoy - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
In this work, we present a simple yet effective framework to address the domain translation problem between different sensor modalities with unique data formats. By relying only on the …
V Purohit, J Luo, Y Chi, Q Guo… - Proceedings of the …, 2024 - openaccess.thecvf.com
The astonishing development of single-photon cameras has created an unprecedented opportunity for scientific and industrial imaging. However the high data throughput …