244 citations · 532 across the 7 of their papers we have counts for
7 papers
Reversible Column Networks
Yuxuan Cai, Yizhuang Zhou, Qi Han +4
We propose a new neural network design paradigm Reversible Column Network (RevCol). The main body of RevCol is composed of multiple copies of subnetworks, named columns respectivel…
RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks
Shanghua Gao, Zhong-Yu Li, Qi Han +2
Temporal/spatial receptive fields of models play an important role in sequential/spatial tasks. Large receptive fields facilitate long-term relations, while small receptive fields…
On the Connection between Local Attention and Dynamic Depth-wise Convolution
Qi Han, Zejia Fan, Qi Dai +4
Vision Transformer (ViT) attains state-of-the-art performance in visual recognition, and the variant, Local Vision Transformer, makes further improvements. The major component in L…
Global2Local: Efficient Structure Search for Video Action Segmentation
Shang-Hua Gao, Qi Han, Zhong-Yu Li +3
Temporal receptive fields of models play an important role in action segmentation. Large receptive fields facilitate the long-term relations among video clips while small receptive…
Delving Deep into Label Smoothing
Chang-Bin Zhang, Peng-Tao Jiang, Qibin Hou +4
Label smoothing is an effective regularization tool for deep neural networks (DNNs), which generates soft labels by applying a weighted average between the uniform distribution and…
Dependency Aware Filter Pruning
Kai Zhao, Xin-Yu Zhang, Qi Han +1
Convolutional neural networks (CNNs) are typically over-parameterized, bringing considerable computational overhead and memory footprint in inference. Pruning a proportion of unimp…
Deep Hough Transform for Semantic Line Detection
Kai Zhao, Qi Han, Chang-Bin Zhang +2
We focus on a fundamental task of detecting meaningful line structures, a.k.a. semantic line, in natural scenes. Many previous methods regard this problem as a special case of obje…