490 citations · 575 across the 12 of their papers we have counts for
6 papers · 1 filter
SurroundNet: Towards Effective Low-Light Image Enhancement
Fei Zhou, Xin Sun, Junyu Dong +2
Although Convolution Neural Networks (CNNs) has made substantial progress in the low-light image enhancement task, one critical problem of CNNs is the paradox of model complexity a…
Knowledge Distillation via Instance-level Sequence Learning
Haoran Zhao, Xin Sun, Junyu Dong +2
Recently, distillation approaches are suggested to extract general knowledge from a teacher network to guide a student network. Most of the existing methods transfer knowledge from…
Gaussian Dynamic Convolution for Efficient Single-Image Segmentation
Xin Sun, Changrui Chen, Xiaorui Wang +3
Interactive single-image segmentation is ubiquitous in the scientific and commercial imaging software. In this work, we focus on the single-image segmentation problem only with som…
Network Embedding via Deep Prediction Model
Xin Sun, Zenghui Song, Yongbo Yu +3
Network-structured data becomes ubiquitous in daily life and is growing at a rapid pace. It presents great challenges to feature engineering due to the high non-linearity and spars…
Dual Discriminator Adversarial Distillation for Data-free Model Compression
Haoran Zhao, Xin Sun, Junyu Dong +2
Knowledge distillation has been widely used to produce portable and efficient neural networks which can be well applied on edge devices for computer vision tasks. However, almost a…
Similarity Transfer for Knowledge Distillation
Haoran Zhao, Kun Gong, Xin Sun +2
Knowledge distillation is a popular paradigm for learning portable neural networks by transferring the knowledge from a large model into a smaller one. Most existing approaches enh…