activity
20172022
most citedNot All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations

95 citations · 254 across the 30 of their papers we have counts for

collaborators

41 papers

cs.CV20221 cited

Joint Self-Supervised Image-Volume Representation Learning with Intra-Inter Contrastive Clustering

Duy M. H. Nguyen, Hoang Nguyen, Mai T. N. Truong +7

Collecting large-scale medical datasets with fully annotated samples for training of deep networks is prohibitively expensive, especially for 3D volume data. Recent breakthroughs i…

cs.CL20222 cited

Type Information Utilized Event Detection via Multi-Channel GNNs in Electrical Power Systems

Qian Li, Jianxin Li, Lihong Wang +6

Event detection in power systems aims to identify triggers and event types, which helps relevant personnel respond to emergencies promptly and facilitates the optimization of power…

cs.CV202295 cited

Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations

Youwei Liang, Chongjian Ge, Zhan Tong +3

Vision Transformers (ViTs) take all the image patches as tokens and construct multi-head self-attention (MHSA) among them. Complete leverage of these image tokens brings redundant…

cs.LG2022

Self-directed Machine Learning

Wenwu Zhu, Xin Wang, Pengtao Xie

Conventional machine learning (ML) relies heavily on manual design from machine learning experts to decide learning tasks, data, models, optimization algorithms, and evaluation met…

cs.LG2021

Learning by Examples Based on Multi-level Optimization

Shentong Mo, Pengtao Xie

Learning by examples, which learns to solve a new problem by looking into how similar problems are solved, is an effective learning method in human learning. When a student learns…

cs.CL20211 cited

Self-supervised Regularization for Text Classification

Meng Zhou, Zechen Li, Pengtao Xie

Text classification is a widely studied problem and has broad applications. In many real-world problems, the number of texts for training classification models is limited, which re…