Recently, GAN has successfully contributed to making single-image super-resolution (SISR)
methods produce more realistic images. However, natural images have complex distribution …

Attention mechanisms have been found effective for person re-identification (Re-ID).
However, the learned" attentive" features are often not naturally uncorrelated or" diverse" …

Data‐driven approaches, most prominently deep learning, have become powerful tools for
prediction in many domains. A natural question to ask is whether data‐driven methods could …

Due to the fast inference and good performance, discriminative learning methods have been
widely studied in image denoising. However, these methods mostly learn a specific model …

This paper proposes the SVDNet for retrieval problems, with focus on the application of
person re-identification (re-ID). We view each weight vector within a fully connected (FC) …

Person Re-identification (re-ID) has great potential to contribute to video surveillance that
automatically searches and identifies people across different cameras. Heterogeneous …

This paper seeks to answer the question: as the (near-) orthogonality of weights is found to
be a favorable property for training deep convolutional neural networks, how can we enforce …

In federated learning (FL), data does not leave personal devices when they are jointly
training a machine learning model. Instead, these devices share gradients, parameters, or …

In inductive transfer learning, fine-tuning pre-trained convolutional networks substantially
outperforms training from scratch. When using fine-tuning, the underlying assumption is that …

Deep convolutional neural networks are hindered by training instability and feature
redundancy towards further performance improvement. A promising solution is to impose …