74 citations · 164 across the 14 of their papers we have counts for
14 papers
Capturing Co-existing Distortions in User-Generated Content for No-reference Video Quality Assessment
Kun Yuan, Zishang Kong, Chuanchuan Zheng +2
Video Quality Assessment (VQA), which aims to predict the perceptual quality of a video, has attracted raising attention with the rapid development of streaming media technology, s…
Learning Multi-modal Representations by Watching Hundreds of Surgical Video Lectures
Kun Yuan, Vinkle Srivastav, Tong Yu +5
Recent advancements in surgical computer vision applications have been driven by vision-only models, which do not explicitly integrate the rich semantics of language into their des…
Quality-aware Pre-trained Models for Blind Image Quality Assessment
Kai Zhao, Kun Yuan, Ming Sun +2
Blind image quality assessment (BIQA) aims to automatically evaluate the perceived quality of a single image, whose performance has been improved by deep learning-based methods in…
ShowFace: Coordinated Face Inpainting with Memory-Disentangled Refinement Networks
Zhuojie Wu, Xingqun Qi, Zijian Wang +4
Face inpainting aims to complete the corrupted regions of the face images, which requires coordination between the completed areas and the non-corrupted areas. Recently, memory-ori…
BlueFog: Make Decentralized Algorithms Practical for Optimization and Deep Learning
Bicheng Ying, Kun Yuan, Hanbin Hu +2
Decentralized algorithm is a form of computation that achieves a global goal through local dynamics that relies on low-cost communication between directly-connected agents. On larg…
Self-supervised Correlation Mining Network for Person Image Generation
Zijian Wang, Xingqun Qi, Kun Yuan +1
Person image generation aims to perform non-rigid deformation on source images, which generally requires unaligned data pairs for training. Recently, self-supervised methods expres…
A Unified and Refined Convergence Analysis for Non-Convex Decentralized Learning
Sulaiman A. Alghunaim, Kun Yuan
We study the consensus decentralized optimization problem where the objective function is the average of agents private non-convex cost functions; moreover, the agents can only…
Effective Model Sparsification by Scheduled Grow-and-Prune Methods
Xiaolong Ma, Minghai Qin, Fei Sun +7
Deep neural networks (DNNs) are effective in solving many real-world problems. Larger DNN models usually exhibit better quality (e.g., accuracy) but their excessive computation res…
Incorporating Convolution Designs into Visual Transformers
Kun Yuan, Shaopeng Guo, Ziwei Liu +3
Motivated by the success of Transformers in natural language processing (NLP) tasks, there emerge some attempts (e.g., ViT and DeiT) to apply Transformers to the vision domain. How…
Differentiable Network Adaption with Elastic Search Space
Shaopeng Guo, Yujie Wang, Kun Yuan +1
In this paper we propose a novel network adaption method called Differentiable Network Adaption (DNA), which can adapt an existing network to a specific computation budget by adjus…
Learning N:M Fine-grained Structured Sparse Neural Networks From Scratch
Aojun Zhou, Yukun Ma, Junnan Zhu +5
Sparsity in Deep Neural Networks (DNNs) has been widely studied to compress and accelerate the models on resource-constrained environments. It can be generally categorized into uns…
Dynamic Graph: Learning Instance-aware Connectivity for Neural Networks
Kun Yuan, Quanquan Li, Dapeng Chen +2
One practice of employing deep neural networks is to apply the same architecture to all the input instances. However, a fixed architecture may not be representative enough for data…
Learning Connectivity of Neural Networks from a Topological Perspective
Kun Yuan, Quanquan Li, Jing Shao +1
Seeking effective neural networks is a critical and practical field in deep learning. Besides designing the depth, type of convolution, normalization, and nonlinearities, the topol…
Towards Good Practices for Instance Segmentation
Dongdong Yu, Zehuan Yuan, Jinlai Liu +2
Instance Segmentation is an interesting yet challenging task in computer vision. In this paper, we conduct a series of refinements with the Hybrid Task Cascade (HTC) Network, and e…