Search Results for author: Yinpeng Chen

Found 34 papers, 13 papers with code

An Intriguing Property of Geophysics Inversion

no code implementations28 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.

Geophysics

Residual Mixture of Experts

no code implementations20 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.

object-detection Object Detection

The Overlooked Classifier in Human-Object Interaction Recognition

no code implementations10 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.

Classification Human-Object Interaction Detection +3

Extremely Weak Supervision Inversion of Multi-physical Properties

no code implementations3 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).

Geophysics

Improving Vision Transformers for Incremental Learning

no code implementations12 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.

class-incremental learning Incremental Learning

BEVT: BERT Pretraining of Video Transformers

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.

Action Recognition Representation Learning

OpenFWI: Large-Scale Multi-Structural Benchmark Datasets for Seismic Full Waveform Inversion

no code implementations4 Nov 2021 Chengyuan Deng, Shihang Feng, Hanchen Wang, Xitong Zhang, Peng Jin, Yinan Feng, Qili Zeng, Yinpeng Chen, Youzuo Lin

Our study uncovers that the deep learning methods generalize poorly across domains, and the degradation connects to the complexity of subsurface structures.

Geophysics

Unsupervised Finetuning

no code implementations18 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.

Unsupervised Learning of Full-Waveform Inversion: Connecting CNN and Partial Differential Equation in a Loop

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).

Geophysics

MicroNet: Improving Image Recognition with Extremely Low FLOPs

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).

Improve Unsupervised Pretraining for Few-label Transfer

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.

Contrastive Learning

Dynamic Head: Unifying Object Detection Heads with Attentions

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 #7 on Object Detection on COCO minival (using extra training data)

object-detection Object Detection

Dynamic Transfer for Multi-Source Domain Adaptation

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.

Domain Adaptation

Revisiting Dynamic Convolution via Matrix Decomposition

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.

Dimensionality Reduction

Stronger NAS with Weaker Predictors

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.

Neural Architecture Search

Dynamic DETR: End-to-End Object Detection With Dynamic Attention

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.

object-detection Object Detection

Weak NAS Predictor Is All You Need

no code implementations1 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.

Neural Architecture Search

Are Fewer Labels Possible for Few-shot Learning?

no code implementations10 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.

Few-Shot Learning

MicroNet: Towards Image Recognition with Extremely Low FLOPs

no code implementations24 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).

DA-NAS: Data Adapted Pruning for Efficient Neural Architecture Search

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).

Neural Architecture Search

Dynamic ReLU

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.

Dynamic Convolution: Attention over Convolution Kernels

4 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.

Image Classification Keypoint Detection

Unsupervised Domain Adaptation for Object Detection via Cross-Domain Semi-Supervised Learning

no code implementations17 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.

object-detection Object Detection +1

Cross-Domain Complementary Learning Using Pose for Multi-Person Part Segmentation

3 code implementations11 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)

Domain Adaptation Human Part Segmentation +2

Large Scale Incremental Learning

2 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.

Incremental Learning

Rethinking Classification and Localization for Object Detection

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.

Classification General Classification +2

Incremental Classifier Learning with Generative Adversarial Networks

no code implementations2 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.

General Classification

Tensor-Based Human Body Modeling

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.

3D Reconstruction Tensor Decomposition

Cannot find the paper you are looking for? You can Submit a new open access paper.