Deep co-training has been introduced to semi-supervised segmentation and...
As the core building block of vision transformers, attention is a powerf...
We introduce a lightweight network to improve descriptors of keypoints w...
In this study, we dive deep into the unique challenges in semi-supervise...
End-to-end object detection is rapidly progressed after the emergence of...
Video object detection is challenging in the presence of appearance
dete...
The performance of object detection, to a great extent, depends on the
a...
Controversy exists on whether differentiable neural architecture search
...
Feature pyramid has been an efficient method to extract features at diff...
Channel pruning is one of the most important techniques for compressing
...
Although adaptive optimization algorithms such as Adam show fast converg...
Improving sparsity of deep neural networks (DNNs) is essential for netwo...
Batch Normalization (BN) makes output of hidden neuron had zero mean and...
As an indispensable component, Batch Normalization (BN) has successfully...