33 citations · 80 across the 16 of their papers we have counts for
16 papers
Towards Vision Transformer Unrolling Fixed-Point Algorithm: a Case Study on Image Restoration
Peng Qiao, Sidun Liu, Tao Sun +2
The great success of Deep Neural Networks (DNNs) has inspired the algorithmic development of DNN-based Fixed-Point (DNN-FP) for computer vision tasks. DNN-FP methods, trained by Ba…
RFC-HyPGCN: A Runtime Sparse Feature Compress Accelerator for Skeleton-Based GCNs Action Recognition Model with Hybrid Pruning
Dong Wen, Jingfei Jiang, Jinwei Xu +4
Skeleton-based Graph Convolutional Networks (GCNs) models for action recognition have achieved excellent prediction accuracy in the field. However, limited by large model and compu…
Towards Precise End-to-end Weakly Supervised Object Detection Network
Ke Yang, Dongsheng Li, Yong Dou
It is challenging for weakly supervised object detection network to precisely predict the positions of the objects, since there are no instance-level category annotations. Most exi…
Heavy-ball Algorithms Always Escape Saddle Points
Tao Sun, Dongsheng Li, Zhe Quan +3
Nonconvex optimization algorithms with random initialization have attracted increasing attention recently. It has been showed that many first-order methods always avoid saddle poin…
Visual Confusion Label Tree For Image Classification
Yuntao Liu, Yong Dou, Ruochun Jin +1
Convolution neural network models are widely used in image classification tasks. However, the running time of such models is so long that it is not the conforming to the strict rea…
Visual Tree Convolutional Neural Network in Image Classification
Yuntao Liu, Yong Dou, Ruochun Jin +1
In image classification, Convolutional Neural Network(CNN) models have achieved high performance with the rapid development in deep learning. However, some categories in the image…