no code implementations • 17 Apr 2024 • Yongdong Luo, Haojia Lin, Xiawu Zheng, Yigeng Jiang, Fei Chao, Jie Hu, Guannan Jiang, Songan Zhang, Rongrong Ji
3D Visual Grounding (3DVG) and 3D Dense Captioning (3DDC) are two crucial tasks in various 3D applications, which require both shared and complementary information in localization and visual-language relationships.
1 code implementation • 19 Mar 2024 • Yuexiao Ma, Huixia Li, Xiawu Zheng, Feng Ling, Xuefeng Xiao, Rui Wang, Shilei Wen, Fei Chao, Rongrong Ji
Among these techniques, Post-Training Quantization (PTQ) has emerged as a subject of considerable interest due to its noteworthy compression efficiency and cost-effectiveness in the context of training.
1 code implementation • 19 Feb 2024 • Song Guo, Fan Wu, Lei Zhang, Xiawu Zheng, Shengchuan Zhang, Fei Chao, Yiyu Shi, Rongrong Ji
For instance, on the Wikitext2 dataset with LlamaV1-7B at 70% sparsity, our proposed EBFT achieves a perplexity of 16. 88, surpassing the state-of-the-art DSnoT with a perplexity of 75. 14.
1 code implementation • 24 Jan 2024 • Yimin Xu, Nanxi Gao, Zhongyun Shan, Fei Chao, Rongrong Ji
In contrast to traditional image restoration methods, all-in-one image restoration techniques are gaining increased attention for their ability to restore images affected by diverse and unknown corruption types and levels.
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 • 9 Dec 2023 • Lirui Zhao, Yuxin Zhang, Mingbao Lin, Fei Chao, Rongrong Ji
The poor cross-architecture generalization of dataset distillation greatly weakens its practical significance.
1 code implementation • ICCV 2023 • Lijiang Li, Huixia Li, Xiawu Zheng, Jie Wu, Xuefeng Xiao, Rui Wang, Min Zheng, Xin Pan, Fei Chao, Rongrong Ji
Therefore, we propose to search the optimal time steps sequence and compressed model architecture in a unified framework to achieve effective image generation for diffusion models without any further training.
1 code implementation • 23 Aug 2023 • Haojia Lin, Yongdong Luo, Xiawu Zheng, Lijiang Li, Fei Chao, Taisong Jin, Donghao Luo, Yan Wang, Liujuan Cao, Rongrong Ji
This elaborate design enables 3DRefTR to achieve both well-performing 3DRES and 3DREC capacities with only a 6% additional latency compared to the original 3DREC model.
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 • ICCV 2023 • Mengzhao Chen, Wenqi Shao, Peng Xu, Mingbao Lin, Kaipeng Zhang, Fei Chao, Rongrong Ji, Yu Qiao, Ping Luo
Token compression aims to speed up large-scale vision transformers (e. g. ViTs) by pruning (dropping) or merging tokens.
Ranked #4 on Efficient ViTs on ImageNet-1K (with DeiT-S)
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 • CVPR 2023 • Yuexiao Ma, Huixia Li, Xiawu Zheng, Xuefeng Xiao, Rui Wang, Shilei Wen, Xin Pan, Fei Chao, Rongrong Ji
In particular, we first formulate the oscillation in PTQ and prove the problem is caused by the difference in module capacity.
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 • 4 Feb 2023 • Yuxin Zhang, Mingbao Lin, Xunchao Li, Han Liu, Guozhi Wang, Fei Chao, Shuai Ren, Yafei Wen, Xiaoxin Chen, Rongrong Ji
In this paper, we launch the first study on accelerating demoireing networks and propose a dynamic demoireing acceleration method (DDA) towards a real-time deployment on mobile devices.
1 code implementation • ICCV 2023 • Song Guo, Lei Zhang, Xiawu Zheng, Yan Wang, Yuchao Li, Fei Chao, Chenglin Wu, Shengchuan Zhang, Rongrong Ji
In this paper, we try to solve this problem by introducing a principled and unified framework based on Information Bottleneck (IB) theory, which further guides us to an automatic pruning approach.
1 code implementation • CVPR 2023 • Tie Hu, Mingbao Lin, Lizhou You, Fei Chao, Rongrong Ji
In contrast to conventional pixel-to-pixel match methods in feature map distillation, our DCD utilizes teacher discriminator as a transformation to drive intermediate results of the student generator to be perceptually close to corresponding outputs of the teacher generator.
1 code implementation • ICCV 2023 • Mengzhao Chen, Mingbao Lin, Zhihang Lin, Yuxin Zhang, Fei Chao, Rongrong Ji
Due to the subtle designs of the self-motivated paradigm, our SMMix is significant in its smaller training overhead and better performance than other CutMix variants.
1 code implementation • 21 Dec 2022 • Lizhou You, Mingbao Lin, Tie Hu, Fei Chao, Rongrong Ji
This paper proposes a content relationship distillation (CRD) to tackle the over-parameterized generative adversarial networks (GANs) for the serviceability in cutting-edge devices.
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 • CVPR 2023 • Haojia Lin, Xiawu Zheng, Lijiang Li, Fei Chao, Shanshan Wang, Yan Wang, Yonghong Tian, Rongrong Ji
However, the lack of a unified framework to interpret those networks makes any systematic comparison, contrast, or analysis challenging, and practically limits healthy development of the field.
Ranked #2 on 3D Semantic Segmentation on OpenTrench3D
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 • 27 Aug 2022 • Hong Yang, Gongrui Nan, Mingbao Lin, Fei Chao, Yunhang Shen, Ke Li, Rongrong Ji
Finally, the LSA modules are further developed to fully use the prior information in non-shadow regions to cleanse the shadow regions.
1 code implementation • 14 Jun 2022 • Yuxin Zhang, Mingbao Lin, Zhihang Lin, Yiting Luo, Ke Li, Fei Chao, Yongjian Wu, Rongrong Ji
In this paper, we show that the N:M learning can be naturally characterized as a combinatorial problem which searches for the best combination candidate within a finite collection.
2 code implementations • 10 May 2022 • Yimin Xu, Mingbao Lin, Hong Yang, Fei Chao, Rongrong Ji
Inspired by the fact that the color mapping of the non-shadow region is easier to learn, our SADC processes the non-shadow region with a lightweight convolution module in a computationally cheap manner and recovers the shadow region with a more complicated convolution module to ensure the quality of image reconstruction.
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 • 8 Mar 2022 • Mengzhao Chen, Mingbao Lin, Ke Li, Yunhang Shen, Yongjian Wu, Fei Chao, Rongrong Ji
Our proposed CF-ViT is motivated by two important observations in modern ViT models: (1) The coarse-grained patch splitting can locate informative regions of an input image.
1 code implementation • 30 Jan 2022 • Yuxin Zhang, Mingbao Lin, Mengzhao Chen, Fei Chao, Rongrong Ji
We prove that supermask training is to accumulate the criteria of gradient-driven sparsity for both removed and preserved weights, and it can partly solve the independence paradox.
no code implementations • 4 Jan 2022 • Tianshuo Xu, Lijiang Li, Peng Mi, Xiawu Zheng, Fei Chao, Rongrong Ji, Yonghong Tian, Qiang Shen
PSNR-oriented models are a critical class of super-resolution models with applications across various fields.
1 code implementation • CVPR 2022 • Xiawu Zheng, Xiang Fei, Lei Zhang, Chenglin Wu, Fei Chao, Jianzhuang Liu, Wei Zeng, Yonghong Tian, Rongrong Ji
Building upon RMI, we further propose a new search algorithm termed RMI-NAS, facilitating with a theorem to guarantee the global optimal of the searched architecture.
1 code implementation • NeurIPS 2021 • Shaojie Li, Jie Wu, Xuefeng Xiao, Fei Chao, Xudong Mao, Rongrong Ji
In this work, we revisit the role of discriminator in GAN compression and design a novel generator-discriminator cooperative compression scheme for GAN compression, termed GCC.
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.
1 code implementation • 6 Sep 2021 • Xingen Gao, Fei Chao, Changle Zhou, Zhen Ge, Chih-Min Lin, Longzhi Yang, Xiang Chang, Changjing Shang
On error of value function inevitably causes an overestimation phenomenon and has a negative impact on the convergence of the algorithms.
1 code implementation • 14 Jul 2021 • Mingbao Lin, Bohong Chen, Fei Chao, Rongrong Ji
Each filter in our DCFF is firstly given an inter-similarity distribution with a temperature parameter as a filter proxy, on top of which, a fresh Kullback-Leibler divergence based dynamic-coded criterion is proposed to evaluate the filter importance.
1 code implementation • 4 Jun 2021 • Shaokun Zhang, Xiawu Zheng, Chenyi Yang, Yuchao Li, Yan Wang, Fei Chao, Mengdi Wang, Shen Li, Jun Yang, Rongrong Ji
Motivated by the necessity of efficient inference across various constraints on BERT, we propose a novel approach, YOCO-BERT, to achieve compress once and deploy everywhere.
1 code implementation • 31 May 2021 • Mingbao Lin, Yuxin Zhang, Yuchao Li, Bohong Chen, Fei Chao, Mengdi Wang, Shen Li, Yonghong Tian, Rongrong Ji
We also provide a workflow of filter rearrangement that first rearranges the weight matrix in the output channel dimension to derive more influential blocks for accuracy improvements and then applies similar rearrangement to the next-layer weights in the input channel dimension to ensure correct convolutional operations.
1 code implementation • CVPR 2021 • Yuchao Li, Shaohui Lin, Jianzhuang Liu, Qixiang Ye, Mengdi Wang, Fei Chao, Fan Yang, Jincheng Ma, Qi Tian, Rongrong Ji
Channel pruning and tensor decomposition have received extensive attention in convolutional neural network compression.
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.
2 code implementations • 16 Feb 2021 • Mingbao Lin, Rongrong Ji, Zihan Xu, Baochang Zhang, Fei Chao, Chia-Wen Lin, Ling Shao
In this paper, we show that our weight binarization provides an analytical solution by encoding high-magnitude weights into +1s, and 0s otherwise.
no code implementations • 1 Jan 2021 • Xingen Gao, Fei Chao, Changle Zhou, Zhen Ge, Chih-Min Lin, Longzhi Yang, Xiang Chang, Changjing Shang
In the reinforcement learning (RL) algorithms which incorporate function approximation methods, the approximation error of value function inevitably cause overestimation phenomenon and have a negative impact on the convergence of the algorithms.
1 code implementation • 17 Nov 2020 • Shaojie Li, Mingbao Lin, Yan Wang, Fei Chao, Ling Shao, Rongrong Ji
The latter simultaneously distills informative attention maps from both the generator and discriminator of a pre-trained model to the searched generator, effectively stabilizing the adversarial training of our light-weight model.
1 code implementation • arXiv 2020 • Jialin Liu, Fei Chao, Chih-Min Lin
Data augmentation is one of the most effective approaches for improving the accuracy of modern machine learning models, and it is also indispensable to train a deep model for meta-learning.
1 code implementation • arXiv 2019 • Jialin Liu, Fei Chao, Longzhi Yang, Chih-Min Lin, Qiang Shen
This work proposes a method that controls the gradient descent process of the model parameters of a neural network by limiting the model parameters in a low-dimensional latent space.
no code implementations • 25 Sep 2019 • Jialin Liu, Fei Chao, Yu-Chen Lin, Chih-Min Lin
The results show that predicting stock price through price rate of change is better than predicting absolute prices directly.
no code implementations • 19 Sep 2019 • Jialin Liu, Chih-Min Lin, Fei Chao
Market economy closely connects aspects to all walks of life.