Weight-sharing neural architecture search: A battle to shrink the optimization gap

L **e, X Chen, K Bi, L Wei, Y Xu, L Wang… - ACM Computing …, 2021 - dl.acm.org
Neural architecture search (NAS) has attracted increasing attention. In recent years,
individual search methods have been replaced by weight-sharing search methods for higher …

Deep high-resolution representation learning for visual recognition

J Wang, K Sun, T Cheng, B Jiang… - IEEE transactions on …, 2020 - ieeexplore.ieee.org
High-resolution representations are essential for position-sensitive vision problems, such as
human pose estimation, semantic segmentation, and object detection. Existing state-of-the …

Deep high-resolution representation learning for human pose estimation

K Sun, B **ao, D Liu, J Wang - Proceedings of the IEEE …, 2019 - openaccess.thecvf.com
In this paper, we are interested in the human pose estimation problem with a focus on
learning reliable high-resolution representations. Most existing methods recover high …

Short-term load forecasting with deep residual networks

K Chen, K Chen, Q Wang, Z He, J Hu… - IEEE Transactions on …, 2018 - ieeexplore.ieee.org
We present in this paper a model for forecasting short-term electric load based on deep
residual networks. The proposed model is able to integrate domain knowledge and …

COVID-19 chest CT image segmentation--a deep convolutional neural network solution

Q Yan, B Wang, D Gong, C Luo, W Zhao… - arxiv preprint arxiv …, 2020 - arxiv.org
A novel coronavirus disease 2019 (COVID-19) was detected and has spread rapidly across
various countries around the world since the end of the year 2019, Computed Tomography …

COVID-19 chest CT image segmentation network by multi-scale fusion and enhancement operations

Q Yan, B Wang, D Gong, C Luo, W Zhao… - IEEE transactions on …, 2021 - ieeexplore.ieee.org
A novel coronavirus disease 2019 (COVID-19) was detected and has spread rapidly across
various countries around the world since the end of the year 2019. Computed Tomography …

Channel splitting network for single MR image super-resolution

X Zhao, Y Zhang, T Zhang, X Zou - IEEE transactions on image …, 2019 - ieeexplore.ieee.org
High resolution magnetic resonance (MR) imaging is desirable in many clinical applications
due to its contribution to more accurate subsequent analyses and early clinical diagnoses …

Interleaved structured sparse convolutional neural networks

G **e, J Wang, T Zhang, J Lai… - Proceedings of the …, 2018 - openaccess.thecvf.com
In this paper, we study the problem of designing efficient convolutional neural network
architectures with the interest in eliminating the redundancy in convolution kernels. In …

Igcv3: Interleaved low-rank group convolutions for efficient deep neural networks

K Sun, M Li, D Liu, J Wang - arxiv preprint arxiv:1806.00178, 2018 - arxiv.org
In this paper, we are interested in building lightweight and efficient convolutional neural
networks. Inspired by the success of two design patterns, composition of structured sparse …

[PDF][PDF] Demystifying local vision transformer: Sparse connectivity, weight sharing, and dynamic weight

Q Han, Z Fan, Q Dai, L Sun, MM Cheng… - arxiv preprint arxiv …, 2021 - ask.qcloudimg.com
Abstract Vision Transformer (ViT) attains state-of-the-art performance in visual recognition,
and the variant, Local Vision Transformer, makes further improvements. The major …