activity
20172022
most citedUnderstanding and Improving Transformer From a Multi-Particle Dynamic System Point of View

117 citations · 207 across the 12 of their papers we have counts for

collaborators
Showing 2019Show all

7 papers · 1 filter

stat.ML201927 cited

Distillation Early Stopping? Harvesting Dark Knowledge Utilizing Anisotropic Information Retrieval For Overparameterized Neural Network

Bin Dong, Jikai Hou, Yiping Lu +1

Distillation is a method to transfer knowledge from one model to another and often achieves higher accuracy with the same capacity. In this paper, we aim to provide a theoretical u…

eess.IV2019

Annotation-Free Cardiac Vessel Segmentation via Knowledge Transfer from Retinal Images

Fei Yu, Jie Zhao, Yanjun Gong +6

Segmenting coronary arteries is challenging, as classic unsupervised methods fail to produce satisfactory results and modern supervised learning (deep learning) requires manual ann…

cs.LG2019117 cited

Understanding and Improving Transformer From a Multi-Particle Dynamic System Point of View

Yiping Lu, Zhuohan Li, Di He +5

The Transformer architecture is widely used in natural language processing. Despite its success, the design principle of the Transformer remains elusive. In this paper, we provide…

cs.CV2019

NPTC-net: Narrow-Band Parallel Transport Convolutional Neural Network on Point Clouds

Pengfei Jin, Tianhao Lai, Rongjie Lai +1

Convolution plays a crucial role in various applications in signal and image processing, analysis, and recognition. It is also the main building block of convolution neural network…

cs.LG2019

Learning to Discretize: Solving 1D Scalar Conservation Laws via Deep Reinforcement Learning

Yufei Wang, Ziju Shen, Zichao Long +1

Conservation laws are considered to be fundamental laws of nature. It has broad applications in many fields, including physics, chemistry, biology, geology, and engineering. Solvin…

stat.ML2019

You Only Propagate Once: Accelerating Adversarial Training via Maximal Principle

Dinghuai Zhang, Tianyuan Zhang, Yiping Lu +2

Deep learning achieves state-of-the-art results in many tasks in computer vision and natural language processing. However, recent works have shown that deep networks can be vulnera…