no code implementations • 10 May 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.
no code implementations • 19 Apr 2022 • Yang Yang, Yiyang Huang, Ming Shi, Kejiang Chen, Weiming Zhang, Nenghai Yu
Then, put the "Mask" face onto the protected face and generate the masked face, in which the masked face is indistinguishable from "Mask" face.
no code implementations • 5 Apr 2022 • Qiankun Liu, Bin Liu, Yue Wu, Weihai Li, Nenghai Yu
Recent online Multi-Object Tracking (MOT) methods have achieved desirable tracking performance.
1 code implementation • 8 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.
1 code implementation • 2 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.
no code implementations • 2 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.
no code implementations • 4 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)
no code implementations • 19 Dec 2021 • Qidong Huang, Jie Zhang, Wenbo Zhou, WeimingZhang, Nenghai Yu
To this end, we first imitate the target manipulation model with a surrogate model, and then devise a poison perturbation generator to obtain the desired venom.
no code implementations • 15 Dec 2021 • Xi Yang, Jie Zhang, Kejiang Chen, Weiming Zhang, Zehua Ma, Feng Wang, Nenghai Yu
Tracing text provenance can help claim the ownership of text content or identify the malicious users who distribute misleading content like machine-generated fake news.
1 code implementation • 9 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.
1 code implementation • 24 Nov 2021 • Xiaoyi Dong, Jianmin Bao, Ting Zhang, Dongdong Chen, Weiming Zhang, Lu Yuan, Dong Chen, Fang Wen, Nenghai Yu
By contrast, the discrete tokens in NLP field are naturally highly semantic.
Ranked #30 on
Image Classification
on ImageNet
no code implementations • 19 Oct 2021 • Haozhe Chen, Weiming Zhang, Kunlin Liu, Kejiang Chen, Han Fang, Nenghai Yu
As an effective method for intellectual property (IP) protection, model watermarking technology has been applied on a wide variety of deep neural networks (DNN), including speech classification models.
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.
1 code implementation • 8 Sep 2021 • Tao Gong, Kai Chen, Xinjiang Wang, Qi Chu, Feng Zhu, Dahua Lin, Nenghai Yu, Huamin Feng
In this work, considering the features of the same object instance are highly similar among frames in a video, a novel Temporal RoI Align operator is proposed to extract features from other frames feature maps for current frame proposals by utilizing feature similarity.
Ranked #1 on
Video Instance Segmentation
on YouTube-VIS
1 code implementation • ICCV 2021 • Zhenchao Jin, Bin Liu, Qi Chu, Nenghai Yu
Third, we compute the similarities between each pixel representation and the image-level contextual information, the semantic-level contextual information, respectively.
no code implementations • 5 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.
no code implementations • 5 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.
no code implementations • 29 Jul 2021 • Luchuan Song, Bin Liu, Huihui Zhu, Qi Chu, Nenghai Yu
To this end, we propose a multivariate fusion method that analyzes each target through three branches: object, action and motion.
no code implementations • 29 Jul 2021 • Kun Zhao, Luchuan Song, Bin Liu, Qi Chu, Nenghai Yu
Crowd counting is a challenging task due to the issues such as scale variation and perspective variation in real crowd scenes.
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.
4 code implementations • 1 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.
Ranked #11 on
Semantic Segmentation
on ADE20K val
2 code implementations • 15 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.
no code implementations • 9 Apr 2021 • Xiquan Guan, Huamin Feng, Weiming Zhang, Hang Zhou, Jie Zhang, Nenghai Yu
Specifically, we present the reversible watermarking problem of deep convolutional neural networks and utilize the pruning theory of model compression technology to construct a host sequence used for embedding watermarking information by histogram shift.
no code implementations • 14 Mar 2021 • Changtao Miao, Qi Chu, Weihai Li, Tao Gong, Wanyi Zhuang, Nenghai Yu
Over the past several years, in order to solve the problem of malicious abuse of facial manipulation technology, face manipulation detection technology has obtained considerable attention and achieved remarkable progress.
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.
Ranked #1 on
Image-to-Image Translation
on ADE20K Labels-to-Photos
(LPIPS metric)
1 code implementation • 8 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.
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).
no code implementations • CVPR 2021 • Honggu Liu, Xiaodan Li, Wenbo Zhou, Yuefeng Chen, Yuan He, Hui Xue, Weiming Zhang, Nenghai Yu
The remarkable success in face forgery techniques has received considerable attention in computer vision due to security concerns.
1 code implementation • 23 Feb 2021 • Kejiang Chen, Yuefeng Chen, Hang Zhou, Chuan Qin, Xiaofeng Mao, Weiming Zhang, Nenghai Yu
To detect both few-perturbation attacks and large-perturbation attacks, we propose a method beyond image space by a two-stream architecture, in which the image stream focuses on the pixel artifacts and the gradient stream copes with the confidence artifacts.
no code implementations • ICLR 2021 • Guoqing Liu, Chuheng Zhang, Li Zhao, Tao Qin, Jinhua Zhu, Jian Li, Nenghai Yu, Tie-Yan Liu
Recently, various auxiliary tasks have been proposed to accelerate representation learning and improve sample efficiency in deep reinforcement learning (RL).
no code implementations • CVPR 2021 • Tianyi Wei, Dongdong Chen, Wenbo Zhou, Jing Liao, Hanqing Zhao, Weiming Zhang, Nenghai Yu
Image matting is a fundamental and challenging problem in computer vision and graphics.
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.
1 code implementation • 8 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.
no code implementations • 7 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).
no code implementations • 1 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.
1 code implementation • 30 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.
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.
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.
no code implementations • 6 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.
no code implementations • CVPR 2020 • Suichan Li, Bin Liu, Dong-Dong Chen, Qi Chu, Lu Yuan, Nenghai Yu
Motivated by these limitations, this paper proposes to solve the SSL problem by building a novel density-aware graph, based on which the neighborhood information can be easily leveraged and the feature learning and label propagation can also be trained in an end-to-end way.
no code implementations • CVPR 2020 • Yan Lu, Yue Wu, Bin Liu, Tianzhu Zhang, Baopu Li, Qi Chu, Nenghai Yu
In this paper, we tackle the above limitation by proposing a novel cross-modality shared-specific feature transfer algorithm (termed cm-SSFT) to explore the potential of both the modality-shared information and the modality-specific characteristics to boost the re-identification performance.
Cross-Modality Person Re-identification
Person Re-Identification
1 code implementation • 25 Feb 2020 • Jie Zhang, Dong-Dong Chen, Jing Liao, Han Fang, Weiming Zhang, Wenbo Zhou, HAO CUI, Nenghai Yu
In this way, when the attacker trains one surrogate model by using the input-output pairs of the target model, the hidden watermark will be learned and extracted afterward.
1 code implementation • 15 Nov 2019 • Kejiang Chen, Hang Zhou, Yuefeng Chen, Xiaofeng Mao, Yuhong Li, Yuan He, Hui Xue, Weiming Zhang, Nenghai Yu
Recent work has demonstrated that neural networks are vulnerable to adversarial examples.
no code implementations • 25 Sep 2019 • Guoqing Liu, Li Zhao, Pushi Zhang, Jiang Bian, Tao Qin, Nenghai Yu, Tie-Yan Liu
One approach leverages demonstration data in a supervised manner, which is simple and direct, but can only provide supervision signal over those states seen in the demonstrations.
no code implementations • ICCV 2019 • Suichan Li, Dapeng Chen, Bin Liu, Nenghai Yu, Rui Zhao
Learning discriminative image feature embeddings is of great importance to visual recognition.
no code implementations • ICCV 2019 • Jiangfan Han, Xiaoyi Dong, Ruimao Zhang, Dong-Dong Chen, Weiming Zhang, Nenghai Yu, Ping Luo, Xiaogang Wang
Recently, generation-based methods have received much attention since they directly use feed-forward networks to generate the adversarial samples, which avoid the time-consuming iterative attacking procedure in optimization-based and gradient-based methods.
no code implementations • 11 Jul 2019 • Qingnan Fan, Dong-Dong Chen, Lu Yuan, Gang Hua, Nenghai Yu, Baoquan Chen
To overcome this limitation, we propose a new decoupled learning algorithm to learn from the operator parameters to dynamically adjust the weights of a deep network for image operators, denoted as the base network.
no code implementations • 26 Apr 2019 • Guojun Yin, Bin Liu, Huihui Zhu, Tao Gong, Nenghai Yu
Multiple-object tracking and behavior analysis have been the essential parts of surveillance video analysis for public security and urban management.
no code implementations • CVPR 2019 • Guojun Yin, Lu Sheng, Bin Liu, Nenghai Yu, Xiaogang Wang, Jing Shao
Dense captioning aims at simultaneously localizing semantic regions and describing these regions-of-interest (ROIs) with short phrases or sentences in natural language.
no code implementations • CVPR 2019 • Guojun Yin, Bin Liu, Lu Sheng, Nenghai Yu, Xiaogang Wang, Jing Shao
Synthesizing photo-realistic images from text descriptions is a challenging problem.
1 code implementation • ICCV 2019 • Hang Zhou, Kejiang Chen, Weiming Zhang, Han Fang, Wenbo Zhou, Nenghai Yu
We propose a Denoiser and UPsampler Network (DUP-Net) structure as defenses for 3D adversarial point cloud classification, where the two modules reconstruct surface smoothness by dropping or adding points.
no code implementations • 12 Dec 2018 • Huihui Zhu, Bin Liu, Guojun Yin, Yan Lu, Weihai Li, Nenghai Yu
Most existing methods are computation consuming, which cannot satisfy the real-time requirement.
no code implementations • 7 Nov 2018 • Jiayang Liu, Weiming Zhang, Nenghai Yu
Deep Neural Networks (DNNs) have recently led to significant improvements in many fields.
no code implementations • 7 Nov 2018 • Dongdong Hou, Weiming Zhang, Jiayang Liu, Siyan Zhou, Dong-Dong Chen, Nenghai Yu
Reversible data hiding (RDH) is one special type of information hiding, by which the host sequence as well as the embedded data can be both restored from the marked sequence without loss.
no code implementations • 3 Nov 2018 • Xiaoyi Dong, Weiming Zhang, Nenghai Yu
In this paper, we propose an improvement of Adversarial Transformation Networks(ATN) to generate adversarial examples, which can fool white-box models and black-box models with a state of the art performance and won the 2rd place in the non-target task in CAAD 2018.
no code implementations • 19 Sep 2018 • Shuxin Zheng, Qi Meng, Huishuai Zhang, Wei Chen, Nenghai Yu, Tie-Yan Liu
Motivated by this, we propose a new norm \emph{Basis-path Norm} based on a group of linearly independent paths to measure the capacity of neural networks more accurately.
1 code implementation • ECCV 2018 • Qingnan Fan, Dong-Dong Chen, Lu Yuan, Gang Hua, Nenghai Yu, Baoquan Chen
Many different deep networks have been used to approximate, accelerate or improve traditional image operators, such as image smoothing, super-resolution and denoising.
no code implementations • ECCV 2018 • Guojun Yin, Lu Sheng, Bin Liu, Nenghai Yu, Xiaogang Wang, Jing Shao, Chen Change Loy
We show that by encouraging deep message propagation and interactions between local object features and global predicate features, one can achieve compelling performance in recognizing complex relationships without using any linguistic priors.
no code implementations • ICML 2018 • Yingce Xia, Xu Tan, Fei Tian, Tao Qin, Nenghai Yu, Tie-Yan Liu
Many artificial intelligence tasks appear in dual forms like English$\leftrightarrow$French translation and speech$\leftrightarrow$text transformation.
no code implementations • CVPR 2019 • Jiayang Liu, Weiming Zhang, Yiwei Zhang, Dongdong Hou, Yujia Liu, Hongyue Zha, Nenghai Yu
Moreover, secondary adversarial attacks cannot be directly performed to our method because our method is not based on a neural network but based on high-dimensional artificial features and FLD (Fisher Linear Discriminant) ensemble.
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.
no code implementations • NeurIPS 2017 • Yingce Xia, Fei Tian, Lijun Wu, Jianxin Lin, Tao Qin, Nenghai Yu, Tie-Yan Liu
In this work, we introduce the deliberation process into the encoder-decoder framework and propose deliberation networks for sequence generation.
no code implementations • 16 Nov 2017 • Yujia Liu, Weiming Zhang, Shaohua Li, Nenghai Yu
In this paper, we first propose the epsilon-neighborhood attack, which can fool the defensively distilled networks with 100% success rate in the white-box setting, and it is fast to generate adversarial examples with good visual quality.
no code implementations • ICCV 2017 • Qi Chu, Wanli Ouyang, Hongsheng Li, Xiaogang Wang, Bin Liu, Nenghai Yu
The visibility map of the target is learned and used for inferring the spatial attention map.
1 code implementation • ICML 2017 • Yingce Xia, Tao Qin, Wei Chen, Jiang Bian, Nenghai Yu, Tie-Yan Liu
Many supervised learning tasks are emerged in dual forms, e. g., English-to-French translation vs. French-to-English translation, speech recognition vs. text to speech, and image classification vs. image generation.
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.
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.
2 code implementations • CVPR 2017 • Feng Zhu, Hongsheng Li, Wanli Ouyang, Nenghai Yu, Xiaogang Wang
Analysis of the learned SRN model demonstrates that it can effectively capture both semantic and spatial relations of labels for improving classification performance.
Ranked #5 on
Multi-Label Classification
on NUS-WIDE
1 code implementation • NeurIPS 2016 • Yingce Xia, Di He, Tao Qin, Li-Wei Wang, Nenghai Yu, Tie-Yan Liu, Wei-Ying Ma
Based on the feedback signals generated during this process (e. g., the language-model likelihood of the output of a model, and the reconstruction error of the original sentence after the primal and dual translations), we can iteratively update the two models until convergence (e. g., using the policy gradient methods).
1 code implementation • 28 Oct 2016 • Yue Wu, Steven C. H. Hoi, Chenghao Liu, Jing Lu, Doyen Sahoo, Nenghai Yu
SOL is an open-source library for scalable online learning algorithms, and is particularly suitable for learning with high-dimensional data.
no code implementations • ICML 2017 • Shuxin Zheng, Qi Meng, Taifeng Wang, Wei Chen, Nenghai Yu, Zhi-Ming Ma, Tie-Yan Liu
We propose a novel technology to compensate this delay, so as to make the optimization behavior of ASGD closer to that of sequential SGD.
no code implementations • 8 Jul 2016 • Liansheng Zhuang, Zihan Zhou, Jingwen Yin, Shenghua Gao, Zhouchen Lin, Yi Ma, Nenghai Yu
In the literature, most existing graph-based semi-supervised learning (SSL) methods only use the label information of observed samples in the label propagation stage, while ignoring such valuable information when learning the graph.
no code implementations • 1 May 2015 • Yingce Xia, Haifang Li, Tao Qin, Nenghai Yu, Tie-Yan Liu
In this paper, we extend the Thompson sampling to Budgeted MAB, where there is random cost for pulling an arm and the total cost is constrained by a budget.
no code implementations • 27 Sep 2014 • Yue Wu, Steven C. H. Hoi, Tao Mei, Nenghai Yu
However, unlike many second-order learning methods that often suffer from extra high computational cost, we devise a novel smart algorithm for second-order online feature selection using a MaxHeap-based approach, which is not only more effective than the existing first-order approaches, but also significantly more efficient and scalable for large-scale feature selection with ultra-high dimensional sparse data, as validated from our extensive experiments.
no code implementations • NeurIPS 2009 • Lei Wu, Rong Jin, Steven C. Hoi, Jianke Zhu, Nenghai Yu
Learning distance functions with side information plays a key role in many machine learning and data mining applications.