Search Results for author: Dongdong Chen

Found 61 papers, 34 papers with code

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

Bringing Old Films Back to Life

1 code implementation31 Mar 2022 Ziyu Wan, Bo Zhang, Dongdong Chen, Jing Liao

We present a learning-based framework, recurrent transformer network (RTN), to restore heavily degraded old films.

Frame

Large-Scale Pre-training for Person Re-identification with Noisy Labels

2 code implementations30 Mar 2022 Dengpan Fu, Dongdong Chen, Hao Yang, Jianmin Bao, Lu Yuan, Lei Zhang, Houqiang Li, Fang Wen, Dong Chen

Since theses ID labels automatically derived from tracklets inevitably contain noises, we develop a large-scale Pre-training framework utilizing Noisy Labels (PNL), which consists of three learning modules: supervised Re-ID learning, prototype-based contrastive learning, and label-guided contrastive learning.

Contrastive Learning Multi-Object Tracking +3

Sampling Theorems for Unsupervised Learning in Linear Inverse Problems

no code implementations23 Mar 2022 Julián Tachella, Dongdong Chen, Mike Davies

In this paper, we present necessary and sufficient sampling conditions for learning the signal model from partial measurements which only depend on the dimension of the model, and the number of operators or properties of the group action that the model is invariant to.

Dictionary Learning Matrix Completion

Shape-invariant 3D Adversarial Point Clouds

1 code implementation8 Mar 2022 Qidong Huang, Xiaoyi Dong, Dongdong Chen, Hang Zhou, Weiming Zhang, Nenghai Yu

In this paper, we propose a novel Point-Cloud Sensitivity Map to boost both the efficiency and imperceptibility of point perturbations.

Self-supervised Transformer for Deepfake Detection

no code implementations2 Mar 2022 Hanqing Zhao, Wenbo Zhou, Dongdong Chen, Weiming Zhang, Nenghai Yu

After pre-training with our method, the model will then be partially fine-tuned for deepfake detection task.

Contrastive Learning DeepFake Detection +3

Protecting Celebrities from DeepFake with Identity Consistency Transformer

1 code implementation2 Mar 2022 Xiaoyi Dong, Jianmin Bao, Dongdong Chen, Ting Zhang, Weiming Zhang, Nenghai Yu, Dong Chen, Fang Wen, Baining Guo

In this work we propose Identity Consistency Transformer, a novel face forgery detection method that focuses on high-level semantics, specifically identity information, and detecting a suspect face by finding identity inconsistency in inner and outer face regions.

Face Swapping

Sampling Theorems for Learning from Incomplete Measurements

no code implementations28 Jan 2022 Julián Tachella, Dongdong Chen, Mike Davies

In many real-world settings, only incomplete measurement data are available which can pose a problem for learning.

Deep Unrolling for Magnetic Resonance Fingerprinting

no code implementations23 Jan 2022 Dongdong Chen, Mike E. Davies, Mohammad Golbabaee

Magnetic Resonance Fingerprinting (MRF) has emerged as a promising quantitative MR imaging approach.

Magnetic Resonance Fingerprinting

Online Multi-Object Tracking with Unsupervised Re-Identification Learning and Occlusion Estimation

no code implementations4 Jan 2022 Qiankun Liu, Dongdong Chen, Qi Chu, Lu Yuan, Bin Liu, Lei Zhang, Nenghai Yu

In addition, such practice of re-identification still can not track those highly occluded objects when they are missed by the detector.

Ranked #6 on Multi-Object Tracking on MOT16 (using extra training data)

Multi-Object Tracking Occlusion Estimation +1

3D Question Answering

no code implementations15 Dec 2021 Shuquan Ye, Dongdong Chen, Songfang Han, Jing Liao

To this end, we propose a novel transformer-based 3DQA framework \textbf{``3DQA-TR"}, which consists of two encoders for exploiting the appearance and geometry information, respectively.

Question Answering Visual Question Answering +1

CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fields

no code implementations9 Dec 2021 Can Wang, Menglei Chai, Mingming He, Dongdong Chen, Jing Liao

Furthermore, we propose an inverse optimization method that accurately projects an input image to the latent codes for manipulation to enable editing on real images.

Novel View Synthesis

HairCLIP: Design Your Hair by Text and Reference Image

1 code implementation9 Dec 2021 Tianyi Wei, Dongdong Chen, Wenbo Zhou, Jing Liao, Zhentao Tan, Lu Yuan, Weiming Zhang, Nenghai Yu

Hair editing is an interesting and challenging problem in computer vision and graphics.

General Facial Representation Learning in a Visual-Linguistic Manner

1 code implementation6 Dec 2021 Yinglin Zheng, Hao Yang, Ting Zhang, Jianmin Bao, Dongdong Chen, Yangyu Huang, Lu Yuan, Dong Chen, Ming Zeng, Fang Wen

In this paper, we study the transfer performance of pre-trained models on face analysis tasks and introduce a framework, called FaRL, for general Facial Representation Learning in a visual-linguistic manner.

 Ranked #1 on Face Parsing on CelebAMask-HQ (using extra training data)

Face Alignment Face Parsing +1

BEVT: BERT Pretraining of Video Transformers

1 code implementation2 Dec 2021 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

Vector Quantized Diffusion Model for Text-to-Image Synthesis

2 code implementations29 Nov 2021 Shuyang Gu, Dong Chen, Jianmin Bao, Fang Wen, Bo Zhang, Dongdong Chen, Lu Yuan, Baining Guo

Our experiments indicate that the VQ-Diffusion model with the reparameterization is fifteen times faster than traditional AR methods while achieving a better image quality.

 Ranked #1 on Text-to-Image Generation on Oxford 102 Flowers (using extra training data)

Denoising Text to image generation +1

Robust Equivariant Imaging: a fully unsupervised framework for learning to image from noisy and partial measurements

1 code implementation25 Nov 2021 Dongdong Chen, Julián Tachella, Mike E. Davies

Deep networks provide state-of-the-art performance in multiple imaging inverse problems ranging from medical imaging to computational photography.

Self-Supervised Learning

Florence: A New Foundation Model for Computer Vision

no code implementations22 Nov 2021 Lu Yuan, Dongdong Chen, Yi-Ling Chen, Noel Codella, Xiyang Dai, Jianfeng Gao, Houdong Hu, Xuedong Huang, Boxin Li, Chunyuan Li, Ce Liu, Mengchen Liu, Zicheng Liu, Yumao Lu, Yu Shi, Lijuan Wang, JianFeng Wang, Bin Xiao, Zhen Xiao, Jianwei Yang, Michael Zeng, Luowei Zhou, Pengchuan Zhang

Computer vision foundation models, which are trained on diverse, large-scale dataset and can be adapted to a wide range of downstream tasks, are critical for this mission to solve real-world computer vision applications.

Action Classification Action Recognition +11

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.

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).

Mobile-Former: Bridging MobileNet and Transformer

2 code implementations12 Aug 2021 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.

Object Detection

Poison Ink: Robust and Invisible Backdoor Attack

no code implementations5 Aug 2021 Jie Zhang, Dongdong Chen, Jing Liao, Qidong Huang, Gang Hua, Weiming Zhang, Nenghai Yu

As the image structure can keep its semantic meaning during the data transformation, such trigger pattern is inherently robust to data transformations.

Backdoor Attack Data Poisoning

Exploring Structure Consistency for Deep Model Watermarking

no code implementations5 Aug 2021 Jie Zhang, Dongdong Chen, Jing Liao, Han Fang, Zehua Ma, Weiming Zhang, Gang Hua, Nenghai Yu

However, little attention has been devoted to the protection of DNNs in image processing tasks.

Data Augmentation

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

CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows

4 code implementations1 Jul 2021 Xiaoyi Dong, Jianmin Bao, Dongdong Chen, Weiming Zhang, Nenghai Yu, Lu Yuan, Dong Chen, Baining Guo

By further pretraining on the larger dataset ImageNet-21K, we achieve 87. 5% Top-1 accuracy on ImageNet-1K and high segmentation performance on ADE20K with 55. 7 mIoU.

Image Classification Semantic Segmentation

Cross-Domain and Disentangled Face Manipulation with 3D Guidance

1 code implementation22 Apr 2021 Can Wang, Menglei Chai, Mingming He, Dongdong Chen, Jing Liao

Face image manipulation via three-dimensional guidance has been widely applied in various interactive scenarios due to its semantically-meaningful understanding and user-friendly controllability.

Domain Adaptation Image Manipulation

E2Style: Improve the Efficiency and Effectiveness of StyleGAN Inversion

2 code implementations15 Apr 2021 Tianyi Wei, Dongdong Chen, Wenbo Zhou, Jing Liao, Weiming Zhang, Lu Yuan, Gang Hua, Nenghai Yu

This paper studies the problem of StyleGAN inversion, which plays an essential role in enabling the pretrained StyleGAN to be used for real image editing tasks.

Face Parsing

Equivariant Imaging: Learning Beyond the Range Space

1 code implementation ICCV 2021 Dongdong Chen, Julián Tachella, Mike E. Davies

In various imaging problems, we only have access to compressed measurements of the underlying signals, hindering most learning-based strategies which usually require pairs of signals and associated measurements for training.

Image Inpainting

High-Fidelity Pluralistic Image Completion with Transformers

3 code implementations ICCV 2021 Ziyu Wan, Jingbo Zhang, Dongdong Chen, Jing Liao

Image completion has made tremendous progress with convolutional neural networks (CNNs), because of their powerful texture modeling capacity.

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

Diverse Semantic Image Synthesis via Probability Distribution Modeling

1 code implementation CVPR 2021 Zhentao Tan, Menglei Chai, Dongdong Chen, Jing Liao, Qi Chu, Bin Liu, Gang Hua, Nenghai Yu

In this paper, we propose a novel diverse semantic image synthesis framework from the perspective of semantic class distributions, which naturally supports diverse generation at semantic or even instance level.

Image-to-Image Translation

Deep Model Intellectual Property Protection via Deep Watermarking

1 code implementation8 Mar 2021 Jie Zhang, Dongdong Chen, Jing Liao, Weiming Zhang, Huamin Feng, Gang Hua, Nenghai Yu

By jointly training the target model and watermark embedding, the extra barrier can even be absorbed into the target model.

Multi-attentional Deepfake Detection

no code implementations CVPR 2021 Hanqing Zhao, Wenbo Zhou, Dongdong Chen, Tianyi Wei, Weiming Zhang, Nenghai Yu

Most of them model deepfake detection as a vanilla binary classification problem, i. e, first use a backbone network to extract a global feature and then feed it into a binary classifier (real/fake).

Data Augmentation DeepFake Detection +1

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

Meta-PU: An Arbitrary-Scale Upsampling Network for Point Cloud

1 code implementation8 Feb 2021 Shuquan Ye, Dongdong Chen, Songfang Han, Ziyu Wan, Jing Liao

Thus, Meta-PU even outperforms the existing methods trained for a specific scale factor only.

Graphics

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

COIN: Contrastive Identifier Network for Breast Mass Diagnosis in Mammography

no code implementations29 Dec 2020 Heyi Li, Dongdong Chen, William H. Nailon, Mike E. Davies, David Laurenson

Computer-aided breast cancer diagnosis in mammography is a challenging problem, stemming from mammographical data scarcity and data entanglement.

Contrastive Learning

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

Efficient Semantic Image Synthesis via Class-Adaptive Normalization

1 code implementation8 Dec 2020 Zhentao Tan, Dongdong Chen, Qi Chu, Menglei Chai, Jing Liao, Mingming He, Lu Yuan, Gang Hua, Nenghai Yu

Spatially-adaptive normalization (SPADE) is remarkably successful recently in conditional semantic image synthesis \cite{park2019semantic}, which modulates the normalized activation with spatially-varying transformations learned from semantic layouts, to prevent the semantic information from being washed away.

Image Generation

Identity-Driven DeepFake Detection

no code implementations7 Dec 2020 Xiaoyi Dong, Jianmin Bao, Dongdong Chen, Weiming Zhang, Nenghai Yu, Dong Chen, Fang Wen, Baining Guo

Our approach takes as input the suspect image/video as well as the target identity information (a reference image or video).

DeepFake Detection Face Swapping

Unsupervised Pre-training for Person Re-identification

1 code implementation CVPR 2021 Dengpan Fu, Dongdong Chen, Jianmin Bao, Hao Yang, Lu Yuan, Lei Zhang, Houqiang Li, Dong Chen

In this paper, we present a large scale unlabeled person re-identification (Re-ID) dataset "LUPerson" and make the first attempt of performing unsupervised pre-training for improving the generalization ability of the learned person Re-ID feature representation.

Ranked #2 on Person Re-Identification on Market-1501 (using extra training data)

Data Augmentation Person Re-Identification +1

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).

LG-GAN: Label Guided Adversarial Network for Flexible Targeted Attack of Point Cloud-based Deep Networks

no code implementations1 Nov 2020 Hang Zhou, Dongdong Chen, Jing Liao, Weiming Zhang, Kejiang Chen, Xiaoyi Dong, Kunlin Liu, Gang Hua, Nenghai Yu

To overcome these shortcomings, this paper proposes a novel label guided adversarial network (LG-GAN) for real-time flexible targeted point cloud attack.

MichiGAN: Multi-Input-Conditioned Hair Image Generation for Portrait Editing

1 code implementation30 Oct 2020 Zhentao Tan, Menglei Chai, Dongdong Chen, Jing Liao, Qi Chu, Lu Yuan, Sergey Tulyakov, Nenghai Yu

In this paper, we present MichiGAN (Multi-Input-Conditioned Hair Image GAN), a novel conditional image generation method for interactive portrait hair manipulation.

Conditional Image Generation

Passport-aware Normalization for Deep Model Protection

1 code implementation NeurIPS 2020 Jie Zhang, Dongdong Chen, Jing Liao, Weiming Zhang, Gang Hua, Nenghai Yu

Only when the model IP is suspected to be stolen by someone, the private passport-aware branch is added back for ownership verification.

Model Compression

GreedyFool: Distortion-Aware Sparse Adversarial Attack

1 code implementation NeurIPS 2020 Xiaoyi Dong, Dongdong Chen, Jianmin Bao, Chuan Qin, Lu Yuan, Weiming Zhang, Nenghai Yu, Dong Chen

Sparse adversarial samples are a special branch of adversarial samples that can fool the target model by only perturbing a few pixels.

Adversarial Attack

Compressive MR Fingerprinting reconstruction with Neural Proximal Gradient iterations

1 code implementation27 Jun 2020 Dongdong Chen, Mike E. Davies, Mohammad Golbabaee

Consistency of the predictions with respect to the physical forward model is pivotal for reliably solving inverse problems.

De-aliasing Magnetic Resonance Fingerprinting

Rethinking Spatially-Adaptive Normalization

no code implementations6 Apr 2020 Zhentao Tan, Dongdong Chen, Qi Chu, Menglei Chai, Jing Liao, Mingming He, Lu Yuan, Nenghai Yu

Despite its impressive performance, a more thorough understanding of the true advantages inside the box is still highly demanded, to help reduce the significant computation and parameter overheads introduced by these new structures.

Image Generation

Learning Discriminative Representation with Signed Laplacian Restricted Boltzmann Machine

no code implementations28 Aug 2018 Dongdong Chen, Jiancheng Lv, Mike E. Davies

We investigate the potential of a restricted Boltzmann Machine (RBM) for discriminative representation learning.

Representation Learning

Stereoscopic Neural Style Transfer

no code implementations CVPR 2018 Dongdong Chen, Lu Yuan, Jing Liao, Nenghai Yu, Gang Hua

This paper presents the first attempt at stereoscopic neural style transfer, which responds to the emerging demand for 3D movies or AR/VR.

Style Transfer

Coherent Online Video Style Transfer

no code implementations ICCV 2017 Dongdong Chen, Jing Liao, Lu Yuan, Nenghai Yu, Gang Hua

Training a feed-forward network for fast neural style transfer of images is proven to be successful.

Frame Image Stylization +1

StyleBank: An Explicit Representation for Neural Image Style Transfer

1 code implementation CVPR 2017 Dongdong Chen, Lu Yuan, Jing Liao, Nenghai Yu, Gang Hua

It also enables us to conduct incremental learning to add a new image style by learning a new filter bank while holding the auto-encoder fixed.

Incremental Learning Style Transfer

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