no code implementations • CVPR 2013 • Yinpeng Chen, Zicheng Liu, Zhengyou Zhang
In this paper, we present a novel approach to model 3D human body with variations on both human shape and pose, by exploring a tensor decomposition technique.
no code implementations • ECCV 2018 • Nikolaos Karianakis, Zicheng Liu, Yinpeng Chen, Stefano Soatto
We address the problem of person re-identification from commodity depth sensors.
no code implementations • 2 Feb 2018 • Yue Wu, Yinpeng Chen, Lijuan Wang, Yuancheng Ye, Zicheng Liu, Yandong Guo, Zhengyou Zhang, Yun Fu
To address these problems, we propose (a) a new loss function to combine the cross-entropy loss and distillation loss, (b) a simple way to estimate and remove the unbalance between the old and new classes , and (c) using Generative Adversarial Networks (GANs) to generate historical data and select representative exemplars during generation.
2 code implementations • CVPR 2020 • Yue Wu, Yinpeng Chen, Lu Yuan, Zicheng Liu, Lijuan Wang, Hongzhi Li, Yun Fu
Two head structures (i. e. fully connected head and convolution head) have been widely used in R-CNN based detectors for classification and localization tasks.
4 code implementations • CVPR 2019 • Yue Wu, Yinpeng Chen, Lijuan Wang, Yuancheng Ye, Zicheng Liu, Yandong Guo, Yun Fu
We believe this is because of the combination of two factors: (a) the data imbalance between the old and new classes, and (b) the increasing number of visually similar classes.
3 code implementations • 11 Jul 2019 • Kevin Lin, Lijuan Wang, Kun Luo, Yinpeng Chen, Zicheng Liu, Ming-Ting Sun
On the other hand, if part labels are also available in the real-images during training, our method outperforms the supervised state-of-the-art methods by a large margin.
Ranked #1 on Human Part Segmentation on PASCAL-Part (using extra training data)
1 code implementation • 17 Nov 2019 • Fuxun Yu, Di Wang, Yinpeng Chen, Nikolaos Karianakis, Tong Shen, Pei Yu, Dimitrios Lymberopoulos, Sidi Lu, Weisong Shi, Xiang Chen
In this work, we show that such adversarial-based methods can only reduce the domain style gap, but cannot address the domain content distribution gap that is shown to be important for object detectors.
5 code implementations • CVPR 2020 • Yinpeng Chen, Xiyang Dai, Mengchen Liu, Dong-Dong Chen, Lu Yuan, Zicheng Liu
Light-weight convolutional neural networks (CNNs) suffer performance degradation as their low computational budgets constrain both the depth (number of convolution layers) and the width (number of channels) of CNNs, resulting in limited representation capability.
Ranked #905 on Image Classification on ImageNet
2 code implementations • ECCV 2020 • Yinpeng Chen, Xiyang Dai, Mengchen Liu, Dong-Dong Chen, Lu Yuan, Zicheng Liu
Rectified linear units (ReLU) are commonly used in deep neural networks.
no code implementations • ECCV 2020 • Xiyang Dai, Dong-Dong Chen, Mengchen Liu, Yinpeng Chen, Lu Yuan
One common way is searching on a smaller proxy dataset (e. g., CIFAR-10) and then transferring to the target task (e. g., ImageNet).
no code implementations • 24 Nov 2020 • Yunsheng Li, Yinpeng Chen, Xiyang Dai, Dongdong Chen, Mengchen Liu, Lu Yuan, Zicheng Liu, Lei Zhang, Nuno Vasconcelos
In this paper, we present MicroNet, which is an efficient convolutional neural network using extremely low computational cost (e. g. 6 MFLOPs on ImageNet classification).
no code implementations • 10 Dec 2020 • Suichan Li, Dongdong Chen, Yinpeng Chen, Lu Yuan, Lei Zhang, Qi Chu, Nenghai Yu
We conduct experiments on 10 different few-shot target datasets, and our average few-shot performance outperforms both vanilla inductive unsupervised transfer and supervised transfer by a large margin.
no code implementations • ICCV 2021 • Xiyang Dai, Yinpeng Chen, Jianwei Yang, Pengchuan Zhang, Lu Yuan, Lei Zhang
To mitigate the second limitation of learning difficulty, we introduce a dynamic decoder by replacing the cross-attention module with a ROI-based dynamic attention in the Transformer decoder.
no code implementations • 1 Jan 2021 • Junru Wu, Xiyang Dai, Dongdong Chen, Yinpeng Chen, Mengchen Liu, Ye Yu, Zhangyang Wang, Zicheng Liu, Mei Chen, Lu Yuan
Rather than expecting a single strong predictor to model the whole space, we seek a progressive line of weak predictors that can connect a path to the best architecture, thus greatly simplifying the learning task of each predictor.
1 code implementation • NeurIPS 2021 • Junru Wu, Xiyang Dai, Dongdong Chen, Yinpeng Chen, Mengchen Liu, Ye Yu, Zhangyang Wang, Zicheng Liu, Mei Chen, Lu Yuan
We propose a paradigm shift from fitting the whole architecture space using one strong predictor, to progressively fitting a search path towards the high-performance sub-space through a set of weaker predictors.
1 code implementation • ICLR 2021 • Yunsheng Li, Yinpeng Chen, Xiyang Dai, Mengchen Liu, Dongdong Chen, Ye Yu, Lu Yuan, Zicheng Liu, Mei Chen, Nuno Vasconcelos
It has two limitations: (a) it increases the number of convolutional weights by K-times, and (b) the joint optimization of dynamic attention and static convolution kernels is challenging.
1 code implementation • CVPR 2021 • Yunsheng Li, Lu Yuan, Yinpeng Chen, Pei Wang, Nuno Vasconcelos
However, such a static model is difficult to handle conflicts across multiple domains, and suffers from a performance degradation in both source domains and target domain.
3 code implementations • CVPR 2021 • Xiyang Dai, Yinpeng Chen, Bin Xiao, Dongdong Chen, Mengchen Liu, Lu Yuan, Lei Zhang
In this paper, we present a novel dynamic head framework to unify object detection heads with attentions.
Ranked #3 on Object Detection on COCO 2017 val (AP75 metric)
no code implementations • ICCV 2021 • Suichan Li, Dongdong Chen, Yinpeng Chen, Lu Yuan, Lei Zhang, Qi Chu, Bin Liu, Nenghai Yu
Unsupervised pretraining has achieved great success and many recent works have shown unsupervised pretraining can achieve comparable or even slightly better transfer performance than supervised pretraining on downstream target datasets.
no code implementations • arXiv 2021 • Ying Jin, Yinpeng Chen, Lijuan Wang, JianFeng Wang, Pei Yu, Zicheng Liu, Jenq-Neng Hwang
This paper revisits human-object interaction (HOI) recognition at image level without using supervisions of object location and human pose.
4 code implementations • CVPR 2022 • Yinpeng Chen, Xiyang Dai, Dongdong Chen, Mengchen Liu, Xiaoyi Dong, Lu Yuan, Zicheng Liu
This structure leverages the advantages of MobileNet at local processing and transformer at global interaction.
1 code implementation • ICCV 2021 • Yunsheng Li, Yinpeng Chen, Xiyang Dai, Dongdong Chen, Mengchen Liu, Lu Yuan, Zicheng Liu, Lei Zhang, Nuno Vasconcelos
This paper aims at addressing the problem of substantial performance degradation at extremely low computational cost (e. g. 5M FLOPs on ImageNet classification).
no code implementations • ICLR 2022 • Peng Jin, Xitong Zhang, Yinpeng Chen, Sharon Xiaolei Huang, Zicheng Liu, Youzuo Lin
In particular, we use finite difference to approximate the forward modeling of PDE as a differentiable operator (from velocity map to seismic data) and model its inversion by CNN (from seismic data to velocity map).
no code implementations • 18 Oct 2021 • Suichan Li, Dongdong Chen, Yinpeng Chen, Lu Yuan, Lei Zhang, Qi Chu, Bin Liu, Nenghai Yu
This problem is more challenging than the supervised counterpart, as the low data density in the small-scale target data is not friendly for unsupervised learning, leading to the damage of the pretrained representation and poor representation in the target domain.
2 code implementations • 4 Nov 2021 • Chengyuan Deng, Shihang Feng, Hanchen Wang, Xitong Zhang, Peng Jin, Yinan Feng, Qili Zeng, Yinpeng Chen, Youzuo Lin
The recent success of data-driven FWI methods results in a rapidly increasing demand for open datasets to serve the geophysics community.
1 code implementation • CVPR 2022 • Rui Wang, Dongdong Chen, Zuxuan Wu, Yinpeng Chen, Xiyang Dai, Mengchen Liu, Yu-Gang Jiang, Luowei Zhou, Lu Yuan
This design is motivated by two observations: 1) transformers learned on image datasets provide decent spatial priors that can ease the learning of video transformers, which are often times computationally-intensive if trained from scratch; 2) discriminative clues, i. e., spatial and temporal information, needed to make correct predictions vary among different videos due to large intra-class and inter-class variations.
Ranked #8 on Action Recognition on Diving-48
no code implementations • 12 Dec 2021 • Pei Yu, Yinpeng Chen, Ying Jin, Zicheng Liu
This paper proposes a working recipe of using Vision Transformer (ViT) in class incremental learning.
no code implementations • arXiv 2021 • Ying Jin, Yinpeng Chen, Lijuan Wang, JianFeng Wang, Pei Yu, Lin Liang, Jenq-Neng Hwang, Zicheng Liu
Human-Object Interaction (HOI) recognition is challenging due to two factors: (1) significant imbalance across classes and (2) requiring multiple labels per image.
Ranked #1 on Human-Object Interaction Detection on HICO
no code implementations • 3 Feb 2022 • Shihang Feng, Peng Jin, Xitong Zhang, Yinpeng Chen, David Alumbaugh, Michael Commer, Youzuo Lin
We explore a multi-physics inversion problem from two distinct measurements~(seismic and EM data) to three geophysical properties~(velocity, conductivity, and CO$_2$ saturation).
no code implementations • 10 Mar 2022 • Ying Jin, Yinpeng Chen, Lijuan Wang, JianFeng Wang, Pei Yu, Lin Liang, Jenq-Neng Hwang, Zicheng Liu
Human-Object Interaction (HOI) recognition is challenging due to two factors: (1) significant imbalance across classes and (2) requiring multiple labels per image.
no code implementations • 20 Apr 2022 • Lemeng Wu, Mengchen Liu, Yinpeng Chen, Dongdong Chen, Xiyang Dai, Lu Yuan
In this paper, we propose Residual Mixture of Experts (RMoE), an efficient training pipeline for MoE vision transformers on downstream tasks, such as segmentation and detection.
no code implementations • 28 Apr 2022 • Yinan Feng, Yinpeng Chen, Shihang Feng, Peng Jin, Zicheng Liu, Youzuo Lin
In particular, when dealing with the inversion from seismic data to subsurface velocity governed by a wave equation, the integral results of velocity with Gaussian kernels are linearly correlated to the integral of seismic data with sine kernels.
1 code implementation • CVPR 2022 • Qiankun Liu, Zhentao Tan, Dongdong Chen, Qi Chu, Xiyang Dai, Yinpeng Chen, Mengchen Liu, Lu Yuan, Nenghai Yu
The indices of quantized pixels are used as tokens for the inputs and prediction targets of transformer.
Ranked #6 on Seeing Beyond the Visible on KITTI360-EX
no code implementations • CVPR 2023 • Lingchen Meng, Xiyang Dai, Yinpeng Chen, Pengchuan Zhang, Dongdong Chen, Mengchen Liu, JianFeng Wang, Zuxuan Wu, Lu Yuan, Yu-Gang Jiang
Detection Hub further achieves SoTA performance on UODB benchmark with wide variety of datasets.
1 code implementation • 7 Jul 2022 • Yunsheng Li, Yinpeng Chen, Xiyang Dai, Dongdong Chen, Mengchen Liu, Pei Yu, Jing Yin, Lu Yuan, Zicheng Liu, Nuno Vasconcelos
We formulate this as a learning problem where the goal is to assign operators to proposals, in the detection head, so that the total computational cost is constrained and the precision is maximized.
1 code implementation • 31 Jul 2022 • Yinpeng Chen, Zhiyu Pan, Min Shi, Hao Lu, Zhiguo Cao, Weicai Zhong
Generative adversarial networks (GANs) have been trained to be professional artists able to create stunning artworks such as face generation and image style transfer.
no code implementations • 25 Aug 2022 • Rui Wang, Zuxuan Wu, Dongdong Chen, Yinpeng Chen, Xiyang Dai, Mengchen Liu, Luowei Zhou, Lu Yuan, Yu-Gang Jiang
To avoid significant computational cost incurred by computing self-attention between the large number of local patches in videos, we propose to use very few global tokens (e. g., 6) for a whole video in Transformers to exchange information with 3D-CNNs with a cross-attention mechanism.
no code implementations • 23 Nov 2022 • Yinpeng Chen, Xiyang Dai, Dongdong Chen, Mengchen Liu, Lu Yuan, Zicheng Liu, Youzuo Lin
When transferring to object detection with frozen backbone, QB-Heat outperforms MoCo-v2 and supervised pre-training on ImageNet by 7. 9 and 4. 5 AP respectively.
4 code implementations • CVPR 2023 • Rui Wang, Dongdong Chen, Zuxuan Wu, Yinpeng Chen, Xiyang Dai, Mengchen Liu, Lu Yuan, Yu-Gang Jiang
For the choice of teacher models, we observe that students taught by video teachers perform better on temporally-heavy video tasks, while image teachers transfer stronger spatial representations for spatially-heavy video tasks.
Ranked #1 on Self-Supervised Action Recognition on HMDB51
no code implementations • 17 Feb 2023 • Zhiyu Pan, Yinpeng Chen, Jiale Zhang, Hao Lu, Zhiguo Cao, Weicai Zhong
Observing that similar composition patterns tend to be shared by the cropping boundaries annotated nearly, we argue to find the beauty of composition from the rare samples by clustering the samples with similar cropping boundary annotations, ie, similar composition patterns.
1 code implementation • 27 Feb 2023 • Ziyu Jiang, Yinpeng Chen, Mengchen Liu, Dongdong Chen, Xiyang Dai, Lu Yuan, Zicheng Liu, Zhangyang Wang
This motivates us to shift the paradigm from combining loss at the end, to choosing the proper learning method per network layer.
no code implementations • 27 Apr 2023 • Yinan Feng, Yinpeng Chen, Peng Jin, Shihang Feng, Zicheng Liu, Youzuo Lin
Geophysics has witnessed success in applying deep learning to one of its core problems: full waveform inversion (FWI) to predict subsurface velocity maps from seismic data.
no code implementations • 25 May 2023 • Yinpeng Chen, Xiyang Dai, Dongdong Chen, Mengchen Liu, Lu Yuan, Zicheng Liu, Youzuo Lin
This paper introduces a novel mathematical property applicable to diverse images, referred to as FINOLA (First-Order Norm+Linear Autoregressive).
1 code implementation • 30 May 2023 • Xiang Li, Chung-Ching Lin, Yinpeng Chen, Zicheng Liu, Jinglu Wang, Bhiksha Raj
The paper introduces PaintSeg, a new unsupervised method for segmenting objects without any training.
2 code implementations • 7 Jun 2023 • Zixin Zhu, Xuelu Feng, Dongdong Chen, Jianmin Bao, Le Wang, Yinpeng Chen, Lu Yuan, Gang Hua
The training cost of our asymmetric VQGAN is cheap, and we only need to retrain a new asymmetric decoder while keeping the vanilla VQGAN encoder and StableDiffusion unchanged.
no code implementations • 21 Jun 2023 • Shihang Feng, Hanchen Wang, Chengyuan Deng, Yinan Feng, Yanhua Liu, Min Zhu, Peng Jin, Yinpeng Chen, Youzuo Lin
We conduct comprehensive numerical experiments to explore the relationship between P-wave and S-wave velocities in seismic data.
no code implementations • 28 Jul 2023 • Peng Jin, Yinan Feng, Shihang Feng, Hanchen Wang, Yinpeng Chen, Benjamin Consolvo, Zicheng Liu, Youzuo Lin
This paper investigates the impact of big data on deep learning models to help solve the full waveform inversion (FWI) problem.
1 code implementation • ICCV 2023 • Qidong Huang, Xiaoyi Dong, Dongdong Chen, Yinpeng Chen, Lu Yuan, Gang Hua, Weiming Zhang, Nenghai Yu
Based on our analysis, we provide a simple yet effective way to boost the adversarial robustness of MAE.
no code implementations • 1 Oct 2023 • Xiang Li, Yinpeng Chen, Chung-Ching Lin, Hao Chen, Kai Hu, Rita Singh, Bhiksha Raj, Lijuan Wang, Zicheng Liu
This paper presents a novel approach to object completion, with the primary goal of reconstructing a complete object from its partially visible components.
no code implementations • 19 Oct 2023 • Yinpeng Chen, Dongdong Chen, Xiyang Dai, Mengchen Liu, Lu Yuan, Zicheng Liu, Youzuo Lin
We term this phenomenon hidden waves, as it reveals that, although the speeds of the set of wave equations and autoregressive coefficient matrices are latent, they are both learnable and shared across images.
1 code implementation • 29 Mar 2024 • Xu Ma, Xiyang Dai, Jianwei Yang, Bin Xiao, Yinpeng Chen, Yun Fu, Lu Yuan
We demonstrate that the modulation mechanism is particularly well suited for efficient networks and further tailor the modulation design by proposing the efficient modulation (EfficientMod) block, which is considered the essential building block for our networks.