Few-shot object detection (FSOD) aims to expand an object detector for n...
Few-shot object detection (FSOD) aims to expand an object detector for n...
The generalization power of the pre-trained model is the key for few-sho...
Conventional training of deep neural networks usually requires a substan...
Supervised learning frequently boils down to determining hidden and brig...
Training deep neural networks (DNNs) efficiently is a challenge due to t...
Boosting is a learning scheme that combines weak prediction rules to pro...
Needlets have been recognized as state-of-the-art tools to tackle spheri...
Regularization is a well recognized powerful strategy to improve the
per...
l^q-regularization has been demonstrated to be an attractive technique i...