427 citations · 801 across the 18 of their papers we have counts for
18 papers
CAIT: Triple-Win Compression towards High Accuracy, Fast Inference, and Favorable Transferability For ViTs
Ao Wang, Hui Chen, Zijia Lin +3
Vision Transformers (ViTs) have emerged as state-of-the-art models for various vision tasks recently. However, their heavy computation costs remain daunting for resource-limited de…
Aggregation Signature for Small Object Tracking
Chunlei Liu, Wenrui Ding, Jinyu Yang +4
Small object tracking becomes an increasingly important task, which however has been largely unexplored in computer vision. The great challenges stem from the facts that: 1) small…
ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks
Xiaohan Ding, Yuchen Guo, Guiguang Ding +1
As designing appropriate Convolutional Neural Network (CNN) architecture in the context of a given application usually involves heavy human works or numerous GPU hours, the researc…
Approximated Oracle Filter Pruning for Destructive CNN Width Optimization
Xiaohan Ding, Guiguang Ding, Yuchen Guo +2
It is not easy to design and run Convolutional Neural Networks (CNNs) due to: 1) finding the optimal number of filters (i.e., the width) at each layer is tricky, given an architect…
Centripetal SGD for Pruning Very Deep Convolutional Networks with Complicated Structure
Xiaohan Ding, Guiguang Ding, Yuchen Guo +1
The redundancy is widely recognized in Convolutional Neural Networks (CNNs), which enables to remove unimportant filters from convolutional layers so as to slim the network with ac…
Saliency-Guided Attention Network for Image-Sentence Matching
Zhong Ji, Haoran Wang, Jungong Han +1
This paper studies the task of matching image and sentence, where learning appropriate representations across the multi-modal data appears to be the main challenge. Unlike previous…