323 citations · 2.1k across the 141 of their papers we have counts for
11 papers · 1 filter
Data-Free Adversarial Distillation
Gongfan Fang, Jie Song, Chengchao Shen +3
Knowledge Distillation (KD) has made remarkable progress in the last few years and become a popular paradigm for model compression and knowledge transfer. However, almost all exist…
Hearing Lips: Improving Lip Reading by Distilling Speech Recognizers
Ya Zhao, Rui Xu, Xinchao Wang +3
Lip reading has witnessed unparalleled development in recent years thanks to deep learning and the availability of large-scale datasets. Despite the encouraging results achieved, t…
Dynamic Instance Normalization for Arbitrary Style Transfer
Yongcheng Jing, Xiao Liu, Yukang Ding +4
Prior normalization methods rely on affine transformations to produce arbitrary image style transfers, of which the parameters are computed in a pre-defined way. Such manually-defi…
Deep Model Transferability from Attribution Maps
Jie Song, Yixin Chen, Xinchao Wang +2
Exploring the transferability between heterogeneous tasks sheds light on their intrinsic interconnections, and consequently enables knowledge transfer from one task to another so a…
Customizing Student Networks From Heterogeneous Teachers via Adaptive Knowledge Amalgamation
Chengchao Shen, Mengqi Xue, Xinchao Wang +3
A massive number of well-trained deep networks have been released by developers online. These networks may focus on different tasks and in many cases are optimized for different da…
Knowledge Amalgamation from Heterogeneous Networks by Common Feature Learning
Sihui Luo, Xinchao Wang, Gongfan Fang +3
An increasing number of well-trained deep networks have been released online by researchers and developers, enabling the community to reuse them in a plug-and-play way without acce…
One-pass Multi-task Networks with Cross-task Guided Attention for Brain Tumor Segmentation
Chenhong Zhou, Changxing Ding, Xinchao Wang +2
Class imbalance has emerged as one of the major challenges for medical image segmentation. The model cascade (MC) strategy significantly alleviates the class imbalance issue via ru…
Amalgamating Filtered Knowledge: Learning Task-customized Student from Multi-task Teachers
Jingwen Ye, Xinchao Wang, Yixin Ji +2
Many well-trained Convolutional Neural Network(CNN) models have now been released online by developers for the sake of effortless reproducing. In this paper, we treat such pre-trai…
Not All Parts Are Created Equal: 3D Pose Estimation by Modelling Bi-directional Dependencies of Body Parts
Jue Wang, Shaoli Huang, Xinchao Wang +1
Not all the human body parts have the same~degree of freedom~(DOF) due to the physiological structure. For example, the limbs may move more flexibly and freely than the torso does.…
Student Becoming the Master: Knowledge Amalgamation for Joint Scene Parsing, Depth Estimation, and More
Jingwen Ye, Yixin Ji, Xinchao Wang +3
In this paper, we investigate a novel deep-model reusing task. Our goal is to train a lightweight and versatile student model, without human-labelled annotations, that amalgamates…
A Light Dual-Task Neural Network for Haze Removal
Yu Zhang, Xinchao Wang, Xiaojun Bi +1
Single-image dehazing is a challenging problem due to its ill-posed nature. Existing methods rely on a suboptimal two-step approach, where an intermediate product like a depth map…