no code implementations • 6 Nov 2023 • Siyi Zhang, Cheng Liu, Xiang Li, Xin Zhai, Zhen Wei, Sizhe Li, Xun Ma
The current trend of automating inspections at substations has sparked a surge in interest in the field of transformer image recognition.
no code implementations • 3 Nov 2023 • Weiying Lin, Che Liu, Xin Zhang, Zhen Wei, Sizhe Li, Xun Ma
The process begins with histogram equalization to enhance the original image, followed by the use of Mask RCNN to identify the preliminary positions and outlines of oil tanks, the ground, and areas of potential oil contamination.
1 code implementation • 3 May 2023 • Zhen Wei, Pascal Fua, Michaël Bauerheim
The Latent Space Model (LSM) learns a low-dimensional latent representation of an object from a dataset of various geometries, while the Direct Mapping Model (DMM) builds parameterization on the fly using only one geometry of interest.
1 code implementation • CVPR 2023 • Haobo Jiang, Zheng Dang, Zhen Wei, Jin Xie, Jian Yang, Mathieu Salzmann
Embedded with the inlier/outlier label, the posterior feature distribution is label-dependent and discriminative.
1 code implementation • 6 Oct 2022 • Ping Xue, Yang Lu, Jingfei Chang, Xing Wei, Zhen Wei
In contrast, considering the limited learning ability and information loss caused by the limited representational capability of BNNs, we propose IR$^2$Net to stimulate the potential of BNNs and improve the network accuracy by restricting the input information and recovering the feature information, including: 1) information restriction: for a BNN, by evaluating the learning ability on the input information, discarding some of the information it cannot focus on, and limiting the amount of input information to match its learning ability; 2) information recovery: due to the information loss in forward propagation, the output feature information of the network is not enough to support accurate classification.
no code implementations • 31 Aug 2021 • Jingfei Chang, Yang Lu, Ping Xue, Yiqun Xu, Zhen Wei
We propose a novel adversarial iterative pruning method (AIP) for CNNs based on knowledge transfer.
no code implementations • 19 Apr 2021 • Zhen Wei, Bingkun Liu, Weinong Wang, Yu-Wing Tai
Thus, there is always a great demand in customized data annotations.
1 code implementation • 3 Mar 2021 • Ping Xue, Yang Lu, Jingfei Chang, Xing Wei, Zhen Wei
In this work, we study the binary neural networks (BNNs) of which both the weights and activations are binary (i. e., 1-bit representation).
1 code implementation • 16 Jan 2021 • Jingfei Chang, Yang Lu, Ping Xue, Yiqun Xu, Zhen Wei
While the accuracy loss after pruning based on the structure sensitivity is relatively slight, the process is time-consuming and the algorithm complexity is notable.
no code implementations • 3 Oct 2020 • Jingfei Chang, Yang Lu, Ping Xue, Xing Wei, Zhen Wei
For ResNet with bottlenecks, we use the pruning method with traditional CNN to trim the 3x3 convolutional layer in the middle of the blocks.
2 code implementations • CVPR 2021 • Xiaoliang Dai, Alvin Wan, Peizhao Zhang, Bichen Wu, Zijian He, Zhen Wei, Kan Chen, Yuandong Tian, Matthew Yu, Peter Vajda, Joseph E. Gonzalez
To address this, we present Neural Architecture-Recipe Search (NARS) to search both (a) architectures and (b) their corresponding training recipes, simultaneously.
Ranked #5 on Neural Architecture Search on ImageNet
no code implementations • CVPR 2019 • Zhen Wei, Jingyi Zhang, Li Liu, Fan Zhu, Fumin Shen, Yi Zhou, Si Liu, Yao Sun, Ling Shao
Max pooling can increase both the invariance to spatial perturbations and the non-linearity of the networks.
no code implementations • IEEE Transactions on Image Processing 2019 • Zhen Wei, Si Liu, Yao Sun, Hefei Ling
In this paper, we propose a design scheme for deep learning networks in the face parsing task with promising accuracy and real-time inference speed.
Ranked #6 on Face Parsing on CelebAMask-HQ
no code implementations • CVPR 2018 • True Price, Johannes L. Schönberger, Zhen Wei, Marc Pollefeys, Jan-Michael Frahm
Image-based 3D reconstruction for Internet photo collections has become a robust technology to produce impressive virtual representations of real-world scenes.
no code implementations • 20 Nov 2017 • Hao Dong, Chao Wu, Zhen Wei, Yike Guo
However, current architecture of deep networks suffers the privacy issue that users need to give out their data to the model (typically hosted in a server or a cluster on Cloud) for training or prediction.
no code implementations • CVPR 2017 • Zhen Wei, Yao Sun, Jinqiao Wang, Hanjiang Lai, Si Liu
In this paper, we introduce a novel approach to regulate receptive field in deep image parsing network automatically.
2 code implementations • 25 May 2016 • Jingdong Wang, Zhen Wei, Ting Zhang, Wen-Jun Zeng
Second, in our suggested fused net formed by one deep and one shallow base networks, the flows of the information from the earlier intermediate layer of the deep base network to the output and from the input to the later intermediate layer of the deep base network are both improved.
2 code implementations • CVPR 2016 • Lingxi Xie, Jingdong Wang, Zhen Wei, Meng Wang, Qi Tian
During a long period of time we are combating over-fitting in the CNN training process with model regularization, including weight decay, model averaging, data augmentation, etc.