activity
20182022
most citedUndistillable: Making A Nasty Teacher That CANNOT teach students

19 citations · 34 across the 4 of their papers we have counts for

collaborators

6 papers

cs.CV20222 cited

Topology-Preserving Shape Reconstruction and Registration via Neural Diffeomorphic Flow

Shanlin Sun, Kun Han, Deying Kong +3

Deep Implicit Functions (DIFs) represent 3D geometry with continuous signed distance functions learned through deep neural nets. Recently DIFs-based methods have been proposed to h…

eess.IV202111 cited

AFTer-UNet: Axial Fusion Transformer UNet for Medical Image Segmentation

Xiangyi Yan, Hao Tang, Shanlin Sun +3

Recent advances in transformer-based models have drawn attention to exploring these techniques in medical image segmentation, especially in conjunction with the U-Net model (or its…

cs.CV20212 cited

Recurrent Mask Refinement for Few-Shot Medical Image Segmentation

Hao Tang, Xingwei Liu, Shanlin Sun +2

Although having achieved great success in medical image segmentation, deep convolutional neural networks usually require a large dataset with manual annotations for training and ar…

cs.LG202119 cited

Undistillable: Making A Nasty Teacher That CANNOT teach students

Haoyu Ma, Tianlong Chen, Ting-Kuei Hu +3

Knowledge Distillation (KD) is a widely used technique to transfer knowledge from pre-trained teacher models to (usually more lightweight) student models. However, in certain situa…

cs.AI2019

Dynamically Pruned Message Passing Networks for Large-Scale Knowledge Graph Reasoning

Xiaoran Xu, Wei Feng, Yunsheng Jiang +3

We propose Dynamically Pruned Message Passing Networks (DPMPN) for large-scale knowledge graph reasoning. In contrast to existing models, embedding-based or path-based, we learn an…

cs.CV2018

Content-based Video Relevance Prediction Challenge: Data, Protocol, and Baseline

Mengyi Liu, Xiaohui Xie, Hanning Zhou

Video relevance prediction is one of the most important tasks for online streaming service. Given the relevance of videos and viewer feedbacks, the system can provide personalized…