Numerous task-specific variants of conditional generative adversarial networks have been
developed for image completion. Yet, a serious limitation remains that all existing algorithms …

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 …

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 …

Analyzing representational similarity among neural networks (NNs) is essential for
interpreting or transferring deep models. In application scenarios where numerous NN …

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 …

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 …

The astonishing development of single-photon cameras has created an unprecedented
opportunity for scientific and industrial imaging. However the high data throughput …