1 code implementation • 5 Jan 2024 • Yunshan Zhong, Yuyao Zhou, Yuxin Zhang, Fei Chao, Rongrong Ji
The proposed method, referred to as Unpaired Demoireing (UnDeM), synthesizes pseudo moire images from unpaired datasets, generating pairs with clean images for training demoireing models.
1 code implementation • 16 Nov 2023 • Yunshan Zhong, Jiawei Hu, Mingbao Lin, Mengzhao Chen, Rongrong Ji
Albeit the scalable performance of vision transformers (ViTs), the dense computational costs (training & inference) undermine their position in industrial applications.
no code implementations • 9 Jun 2023 • Yuxin Zhang, Mingbao Lin, Yunshan Zhong, Mengzhao Chen, Fei Chao, Rongrong Ji
This paper presents a Spatial Re-parameterization (SpRe) method for the N:M sparsity in CNNs.
1 code implementation • 14 May 2023 • Yunshan Zhong, Mingbao Lin, Yuyao Zhou, Mengzhao Chen, Yuxin Zhang, Fei Chao, Rongrong Ji
However, in this paper, we investigate existing methods and observe a significant accumulation of quantization errors caused by frequent bit-width switching of weights and activations, leading to limited performance.
1 code implementation • 10 May 2023 • Yunshan Zhong, Mingbao Lin, Jingjing Xie, Yuxin Zhang, Fei Chao, Rongrong Ji
Compared to the common iterative exhaustive search algorithm, our strategy avoids the enumeration of all possible combinations in the universal set, reducing the time complexity from exponential to linear.
1 code implementation • 13 Feb 2023 • Yuxin Zhang, Yiting Luo, Mingbao Lin, Yunshan Zhong, Jingjing Xie, Fei Chao, Rongrong Ji
We focus on addressing the dense backward propagation issue for training efficiency of N:M fine-grained sparsity that preserves at most N out of M consecutive weights and achieves practical speedups supported by the N:M sparse tensor core.
1 code implementation • 8 Dec 2022 • Yunshan Zhong, Lizhou You, Yuxin Zhang, Fei Chao, Yonghong Tian, Rongrong Ji
Specifically, the encoder extracts the shadow feature of a region identity which is then paired with another region identity to serve as the generator input to synthesize a pseudo image.
1 code implementation • 12 Nov 2022 • Yunshan Zhong, Gongrui Nan, Yuxin Zhang, Fei Chao, Rongrong Ji
In QAT, the contemporary experience is that all quantized weights are updated for an entire training process.
1 code implementation • 8 Mar 2022 • Yunshan Zhong, Mingbao Lin, Xunchao Li, Ke Li, Yunhang Shen, Fei Chao, Yongjian Wu, Rongrong Ji
However, these methods suffer from severe performance degradation when quantizing the SR models to ultra-low precision (e. g., 2-bit and 3-bit) with the low-cost layer-wise quantizer.
1 code implementation • CVPR 2022 • Yunshan Zhong, Mingbao Lin, Gongrui Nan, Jianzhuang Liu, Baochang Zhang, Yonghong Tian, Rongrong Ji
In this paper, we observe an interesting phenomenon of intra-class heterogeneity in real data and show that existing methods fail to retain this property in their synthetic images, which causes a limited performance increase.
1 code implementation • 9 Sep 2021 • Yunshan Zhong, Mingbao Lin, Mengzhao Chen, Ke Li, Yunhang Shen, Fei Chao, Yongjian Wu, Rongrong Ji
While post-training quantization receives popularity mostly due to its evasion in accessing the original complete training dataset, its poor performance also stems from scarce images.
2 code implementations • 18 Apr 2021 • Yuxin Zhang, Mingbao Lin, Yunshan Zhong, Fei Chao, Rongrong Ji
Existing studies achieve the sparsity of neural networks via time-consuming weight training or complex searching on networks with expanded width, which greatly limits the applications of network pruning.
no code implementations • ICCV 2019 • Chuchu Han, Jiacheng Ye, Yunshan Zhong, Xin Tan, Chi Zhang, Changxin Gao, Nong Sang
The state-of-the-art methods train the detector individually, and the detected bounding boxes may be sub-optimal for the following re-ID task.
no code implementations • CVPR 2019 • Jian Wang, Yunshan Zhong, Yachun Li, Chi Zhang, Yichen Wei
The estimation of 3D human body pose and shape from a single image has been extensively studied in recent years.