Search Results for author: Kai Chen

Found 115 papers, 44 papers with code

Group R-CNN for Weakly Semi-supervised Object Detection with Points

1 code implementation12 May 2022 Shilong Zhang, Zhuoran Yu, Liyang Liu, Xinjiang Wang, Aojun Zhou, Kai Chen

The core of this task is to train a point-to-box regressor on well-labeled images that can be used to predict credible bounding boxes for each point annotation.

Object Detection Representation Learning +1

TransRank: Self-supervised Video Representation Learning via Ranking-based Transformation Recognition

1 code implementation4 May 2022 Haodong Duan, Nanxuan Zhao, Kai Chen, Dahua Lin

To mitigate this problem, we developed TransRank, a unified framework for recognizing Transformations in a Ranking formulation.

Action Recognition Representation Learning +2

MMRotate: A Rotated Object Detection Benchmark using Pytorch

1 code implementation28 Apr 2022 Yue Zhou, Xue Yang, Gefan Zhang, Jiabao Wang, Yanyi Liu, Liping Hou, Xue Jiang, Xingzhao Liu, Junchi Yan, Chengqi Lyu, Wenwei Zhang, Kai Chen

We present an open-source toolbox, named MMRotate, which provides a coherent algorithm framework of training, inferring, and evaluation for the popular rotated object detection algorithm based on deep learning.

Object Detection

ROMA: Cross-Domain Region Similarity Matching for Unpaired Nighttime Infrared to Daytime Visible Video Translation

no code implementations26 Apr 2022 Zhenjie Yu, Kai Chen, Shuang Li, Bingfeng Han, Chi Harold Liu, Shuigen Wang

To be specific, ROMA could efficiently translate the unpaired nighttime infrared videos into fine-grained daytime visible ones, meanwhile maintain the spatiotemporal consistency via matching the cross-domain region similarity.


Sim-to-Real 6D Object Pose Estimation via Iterative Self-training for Robotic Bin-picking

no code implementations14 Apr 2022 Kai Chen, Rui Cao, Stephen James, Yichuan Li, Yun-hui Liu, Pieter Abbeel, Qi Dou

To continuously improve the quality of pseudo labels, we iterate the above steps by taking the trained student model as a new teacher and re-label real data using the refined teacher model.

6D Pose Estimation using RGB Robotic Grasping

StructToken : Rethinking Semantic Segmentation with Structural Prior

no code implementations23 Mar 2022 Fangjian Lin, Zhanhao Liang, Junjun He, Miao Zheng, Shengwei Tian, Kai Chen

From a perspective on semantic segmentation as per-pixel classification, the previous deep learning-based methods learn the per-pixel representation first through an encoder and a decoder head and then classify each pixel representation to a specific category to obtain the semantic masks.

Semantic Segmentation

Dense Siamese Network

no code implementations21 Mar 2022 Wenwei Zhang, Jiangmiao Pang, Kai Chen, Chen Change Loy

It also extracts a batch of region embeddings that correspond to some sub-regions in the overlapped area to be contrasted for region consistency.

Unsupervised Semantic Segmentation

APRNet: Attention-based Pixel-wise Rendering Network for Photo-Realistic Text Image Generation

no code implementations15 Mar 2022 Yangming Shi, Haisong Ding, Kai Chen, Qiang Huo

Style-guided text image generation tries to synthesize text image by imitating reference image's appearance while keeping text content unaltered.

Image Generation

CODA: A Real-World Road Corner Case Dataset for Object Detection in Autonomous Driving

no code implementations15 Mar 2022 Kaican Li, Kai Chen, Haoyu Wang, Lanqing Hong, Chaoqiang Ye, Jianhua Han, Yukuai Chen, Wei zhang, Chunjing Xu, Dit-yan Yeung, Xiaodan Liang, Zhenguo Li, Hang Xu

One main reason that impedes the development of truly reliably self-driving systems is the lack of public datasets for evaluating the performance of object detectors on corner cases.

Autonomous Driving Object Detection

RotateQVS: Representing Temporal Information as Rotations in Quaternion Vector Space for Temporal Knowledge Graph Completion

no code implementations ACL 2022 Kai Chen, Ye Wang, Yitong Li, Aiping Li

Temporal factors are tied to the growth of facts in realistic applications, such as the progress of diseases and the development of political situation, therefore, research on Temporal Knowledge Graph (TKG) attracks much attention.

Knowledge Graph Completion Link Prediction +2

GCFSR: a Generative and Controllable Face Super Resolution Method Without Facial and GAN Priors

no code implementations14 Mar 2022 Jingwen He, Wu Shi, Kai Chen, Lean Fu, Chao Dong

The style modulation aims to generate realistic face details and the feature modulation dynamically fuses the multi-level encoded features and the generated ones conditioned on the upscaling factor.

Face Hallucination Image Super-Resolution

No Free Lunch Theorem for Security and Utility in Federated Learning

no code implementations11 Mar 2022 Xiaojin Zhang, Hanlin Gu, Lixin Fan, Kai Chen, Qiang Yang

In a federated learning scenario where multiple parties jointly learn a model from their respective data, there exist two conflicting goals for the choice of appropriate algorithms.

Federated Learning

PPA: Preference Profiling Attack Against Federated Learning

no code implementations10 Feb 2022 Chunyi Zhou, Yansong Gao, Anmin Fu, Kai Chen, Zhiyang Dai, Zhi Zhang, Minhui Xue, Yuqing Zhang

In this work, we reveal a new type of privacy inference attack, coined Preference Profiling Attack (PPA), that accurately profiles private preferences of a local user.

Federated Learning Inference Attack

Efficient Data-Plane Memory Scheduling for In-Network Aggregation

no code implementations17 Jan 2022 Hao Wang, Yuxuan Qin, ChonLam Lao, Yanfang Le, Wenfei Wu, Kai Chen

However, switch memory is scarce compared to the volume of gradients transmitted in distributed training.

Efficient DNN Training with Knowledge-Guided Layer Freezing

no code implementations17 Jan 2022 Yiding Wang, Decang Sun, Kai Chen, Fan Lai, Mosharaf Chowdhury

To explore this, we first introduce the notion of training plasticity to quantify the training progress of internal DNN layers.


OCSampler: Compressing Videos to One Clip with Single-step Sampling

no code implementations12 Jan 2022 Jintao Lin, Haodong Duan, Kai Chen, Dahua Lin, LiMin Wang

Recent works prefer to formulate frame sampling as a sequential decision task by selecting frames one by one according to their importance, while we present a new paradigm of learning instance-specific video condensation policies to select informative frames for representing the entire video only in a single step.

Frame Video Recognition

TAGPerson: A Target-Aware Generation Pipeline for Person Re-identification

1 code implementation28 Dec 2021 Kai Chen, Weihua Chen, Tao He, Rong Du, Fan Wang, Xiuyu Sun, Yuchen Guo, Guiguang Ding

In TAGPerson, we extract information from target scenes and use them to control our parameterized rendering process to generate target-aware synthetic images, which would hold a smaller gap to the real images in the target domain.

Person Re-Identification

Automatic Configuration for Optimal Communication Scheduling in DNN Training

no code implementations27 Dec 2021 Yiqing Ma, Hao Wang, Yiming Zhang, Kai Chen

ByteScheduler partitions and rearranges tensor transmissions to improve the communication efficiency of distributed Deep Neural Network (DNN) training.

LAVT: Language-Aware Vision Transformer for Referring Image Segmentation

2 code implementations4 Dec 2021 Zhao Yang, Jiaqi Wang, Yansong Tang, Kai Chen, Hengshuang Zhao, Philip H. S. Torr

Referring image segmentation is a fundamental vision-language task that aims to segment out an object referred to by a natural language expression from an image.

Referring Expression Referring Expression Segmentation +1

Few-Shot Object Detection via Association and DIscrimination

1 code implementation NeurIPS 2021 Yuhang Cao, Jiaqi Wang, Ying Jin, Tong Wu, Kai Chen, Ziwei Liu, Dahua Lin

1) In the association step, in contrast to implicitly leveraging multiple base classes, we construct a compact novel class feature space via explicitly imitating a specific base class feature space.

Few-Shot Object Detection Semantic Similarity +1

DBIA: Data-free Backdoor Injection Attack against Transformer Networks

no code implementations22 Nov 2021 Peizhuo Lv, Hualong Ma, Jiachen Zhou, Ruigang Liang, Kai Chen, Shengzhi Zhang, Yunfei Yang

In this paper, we propose DBIA, a novel data-free backdoor attack against the CV-oriented transformer networks, leveraging the inherent attention mechanism of transformers to generate triggers and injecting the backdoor using the poisoned surrogate dataset.

Backdoor Attack Image Classification

Attacking Video Recognition Models with Bullet-Screen Comments

1 code implementation29 Oct 2021 Kai Chen, Zhipeng Wei, Jingjing Chen, Zuxuan Wu, Yu-Gang Jiang

On both UCF-101 and HMDB-51 datasets, our BSC attack method can achieve about 90\% fooling rate when attacking three mainstream video recognition models, while only occluding \textless 8\% areas in the video.

Adversarial Attack Video Recognition

The Nuts and Bolts of Adopting Transformer in GANs

no code implementations25 Oct 2021 Rui Xu, Xiangyu Xu, Kai Chen, Bolei Zhou, Chen Change Loy

Transformer becomes prevalent in computer vision, especially for high-level vision tasks.

Image Generation

Quantitative relations among causality measures with applications to nonlinear pulse-output network reconstruction

no code implementations17 Oct 2021 Zhong-qi K. Tian, Kai Chen, Songting Li, David W. McLaughlin, Douglas Zhou

However, the interpretation of causal connectivity remains to be fully clarified, in particular, how causal connectivity depends on causality measures and how causal connectivity relates to structural connectivity.

Foreground-attention in neural decoding: Guiding Loop-Enc-Dec to reconstruct visual stimulus images from fMRI

no code implementations29 Sep 2021 Kai Chen, Yongqiang Ma, Mingyang Sheng, Nanning Zheng

Inspired by the mechanism of human visual attention, in this paper, we propose a novel method of reconstructing visual stimulus images, which first decodes the distribution of visual attention from fMRI, and then reconstructs the visual images guided by visual attention.

Image Reconstruction

Temporal RoI Align for Video Object Recognition

1 code implementation8 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.

Frame Instance Segmentation +4

MultiSiam: Self-supervised Multi-instance Siamese Representation Learning for Autonomous Driving

1 code implementation ICCV 2021 Kai Chen, Lanqing Hong, Hang Xu, Zhenguo Li, Dit-yan Yeung

By pre-training on SODA10M, a large-scale autonomous driving dataset, MultiSiam exceeds the ImageNet pre-trained MoCo-v2, demonstrating the potential of domain-specific pre-training.

Autonomous Driving Image Clustering +2

Towards Balanced Learning for Instance Recognition

no code implementations23 Aug 2021 Jiangmiao Pang, Kai Chen, Qi Li, Zhihai Xu, Huajun Feng, Jianping Shi, Wanli Ouyang, Dahua Lin

In this work, we carefully revisit the standard training practice of detectors, and find that the detection performance is often limited by the imbalance during the training process, which generally consists in three levels - sample level, feature level, and objective level.

Category-Level 6D Object Pose Estimation via Cascaded Relation and Recurrent Reconstruction Networks

no code implementations19 Aug 2021 Jiaze Wang, Kai Chen, Qi Dou

Furthermore, we design a recurrent reconstruction network for iterative residual refinement to progressively improve the reconstruction and correspondence estimations from coarse to fine.

6D Pose Estimation 6D Pose Estimation using RGB +1

Practical and Secure Federated Recommendation with Personalized Masks

no code implementations18 Aug 2021 Liu Yang, Ben Tan, Bo Liu, Vincent W. Zheng, Kai Chen, Qiang Yang

Federated masked matrix factorization could protect the data privacy in federated recommender systems without sacrificing efficiency or efficacy.

Federated Learning Recommendation Systems

Aegis: A Trusted, Automatic and Accurate Verification Framework for Vertical Federated Learning

no code implementations16 Aug 2021 Cengguang Zhang, Junxue Zhang, Di Chai, Kai Chen

In this paper, we present Aegis, a trusted, automatic, and accurate verification framework to verify the security of VFL jobs.

Federated Learning

MMOCR: A Comprehensive Toolbox for Text Detection, Recognition and Understanding

1 code implementation14 Aug 2021 Zhanghui Kuang, Hongbin Sun, Zhizhong Li, Xiaoyu Yue, Tsui Hin Lin, Jianyong Chen, Huaqiang Wei, Yiqin Zhu, Tong Gao, Wenwei Zhang, Kai Chen, Wayne Zhang, Dahua Lin

We present MMOCR-an open-source toolbox which provides a comprehensive pipeline for text detection and recognition, as well as their downstream tasks such as named entity recognition and key information extraction.

Key information extraction Named Entity Recognition +1

I2V-GAN: Unpaired Infrared-to-Visible Video Translation

1 code implementation2 Aug 2021 Shuang Li, Bingfeng Han, Zhenjie Yu, Chi Harold Liu, Kai Chen, Shuigen Wang

Human vision is often adversely affected by complex environmental factors, especially in night vision scenarios.

Object Detection Translation

HAFLO: GPU-Based Acceleration for Federated Logistic Regression

no code implementations29 Jul 2021 Xiaodian Cheng, Wanhang Lu, Xinyang Huang, Shuihai Hu, Kai Chen

In recent years, federated learning (FL) has been widely applied for supporting decentralized collaborative learning scenarios.

Federated Learning

K-Net: Towards Unified Image Segmentation

1 code implementation NeurIPS 2021 Wenwei Zhang, Jiangmiao Pang, Kai Chen, Chen Change Loy

The framework, named K-Net, segments both instances and semantic categories consistently by a group of learnable kernels, where each kernel is responsible for generating a mask for either a potential instance or a stuff class.

Instance Segmentation Panoptic Segmentation

SODA10M: A Large-Scale 2D Self/Semi-Supervised Object Detection Dataset for Autonomous Driving

no code implementations21 Jun 2021 Jianhua Han, Xiwen Liang, Hang Xu, Kai Chen, Lanqing Hong, Jiageng Mao, Chaoqiang Ye, Wei zhang, Zhenguo Li, Xiaodan Liang, Chunjing Xu

Experiments show that SODA10M can serve as a promising pre-training dataset for different self-supervised learning methods, which gives superior performance when fine-tuning with different downstream tasks (i. e., detection, semantic/instance segmentation) in autonomous driving domain.

Autonomous Driving Instance Segmentation +4

DeepObliviate: A Powerful Charm for Erasing Data Residual Memory in Deep Neural Networks

no code implementations13 May 2021 Yingzhe He, Guozhu Meng, Kai Chen, Jinwen He, Xingbo Hu

Compared to the method of retraining from scratch, our approach can achieve 99. 0%, 95. 0%, 91. 9%, 96. 7%, 74. 1% accuracy rates and 66. 7$\times$, 75. 0$\times$, 33. 3$\times$, 29. 4$\times$, 13. 7$\times$ speedups on the MNIST, SVHN, CIFAR-10, Purchase, and ImageNet datasets, respectively.

Revisiting Skeleton-based Action Recognition

2 code implementations28 Apr 2021 Haodong Duan, Yue Zhao, Kai Chen, Dahua Lin, Bo Dai

In this work, we propose PoseC3D, a new approach to skeleton-based action recognition, which relies on a 3D heatmap stack instead of a graph sequence as the base representation of human skeletons.

Action Recognition Group Activity Recognition +2

HufuNet: Embedding the Left Piece as Watermark and Keeping the Right Piece for Ownership Verification in Deep Neural Networks

1 code implementation25 Mar 2021 Peizhuo Lv, Pan Li, Shengzhi Zhang, Kai Chen, Ruigang Liang, Yue Zhao, Yingjiu Li

Most existing solutions embed backdoors in DNN model training such that DNN ownership can be verified by triggering distinguishable model behaviors with a set of secret inputs.

SoK: A Modularized Approach to Study the Security of Automatic Speech Recognition Systems

1 code implementation19 Mar 2021 Yuxuan Chen, Jiangshan Zhang, Xuejing Yuan, Shengzhi Zhang, Kai Chen, XiaoFeng Wang, Shanqing Guo

In this paper, we present our systematization of knowledge for ASR security and provide a comprehensive taxonomy for existing work based on a modularized workflow.

Adversarial Attack Automatic Speech Recognition +1

Recent Advances in Data-Driven Wireless Communication Using Gaussian Processes: A Comprehensive Survey

no code implementations18 Mar 2021 Kai Chen, Qinglei Kong, Yijue Dai, Yue Xu, Feng Yin, Lexi Xu, Shuguang Cui

Empowered by big data and machine learning, next-generation data-driven communication systems will be intelligent with the characteristics of expressiveness, scalability, interpretability, and especially uncertainty modeling, which can confidently involve diversified latent demands and personalized services in the foreseeable future.

Gaussian Processes

ICDAR2019 Competition on Scanned Receipt OCR and Information Extraction

1 code implementation18 Mar 2021 Zheng Huang, Kai Chen, Jianhua He, Xiang Bai, Dimosthenis Karatzas, Shjian Lu, C. V. Jawahar

In this competition, we set up three tasks, namely, Scanned Receipt Text Localisation (Task 1), Scanned Receipt OCR (Task 2) and Key Information Extraction from Scanned Receipts (Task 3).

Key information extraction Optical Character Recognition

NAST: Non-Autoregressive Spatial-Temporal Transformer for Time Series Forecasting

1 code implementation10 Feb 2021 Kai Chen, Guang Chen, Dan Xu, Lijun Zhang, Yuyao Huang, Alois Knoll

Although Transformer has made breakthrough success in widespread domains especially in Natural Language Processing (NLP), applying it to time series forecasting is still a great challenge.

Time Series Time Series Forecasting

Fast and Reliable Probabilistic Face Embeddings in the Wild

1 code implementation8 Feb 2021 Kai Chen, Qi Lv, Taihe Yi

In addition, an identification preserving loss is proposed to improve the discriminative of the MLS metric, and a multi-layer feature fusion module is proposed to improve the neural network's uncertainty estimation ability.

Face Recognition

SGPA: Structure-Guided Prior Adaptation for Category-Level 6D Object Pose Estimation

no code implementations ICCV 2021 Kai Chen, Qi Dou

The prior adaptation intrinsically associates the adopted prior with different objects, from which we can accurately reconstruct the 3D canonical model of the specific object for pose estimation.

6D Pose Estimation using RGB

UMLE: Unsupervised Multi-discriminator Network for Low Light Enhancement

no code implementations24 Dec 2020 Yangyang Qu, Kai Chen, Chao Liu, Yongsheng Ou

To address this problem, we propose a real-time unsupervised generative adversarial network (GAN) containing multiple discriminators, i. e. a multi-scale discriminator, a texture discriminator, and a color discriminator.

Low-Light Image Enhancement

Positional Encoding as Spatial Inductive Bias in GANs

no code implementations CVPR 2021 Rui Xu, Xintao Wang, Kai Chen, Bolei Zhou, Chen Change Loy

In this work, taking SinGAN and StyleGAN2 as examples, we show that such capability, to a large extent, is brought by the implicit positional encoding when using zero padding in the generators.

Image Manipulation Translation

CARAFE++: Unified Content-Aware ReAssembly of FEatures

no code implementations7 Dec 2020 Jiaqi Wang, Kai Chen, Rui Xu, Ziwei Liu, Chen Change Loy, Dahua Lin

Feature reassembly, i. e. feature downsampling and upsampling, is a key operation in a number of modern convolutional network architectures, e. g., residual networks and feature pyramids.

Image Inpainting Instance Segmentation +2

RRCN: A Reinforced Random Convolutional Network based Reciprocal Recommendation Approach for Online Dating

no code implementations25 Nov 2020 Linhao Luo, Liqi Yang, Ju Xin, Yixiang Fang, Xiaofeng Zhang, Xiaofei Yang, Kai Chen, Zhiyuan Zhang, Kai Liu

In particular, we technically propose a novel random CNN component that can randomly convolute non-adjacent features to capture their interaction information and learn feature embeddings of key attributes to make the final recommendation.

FedEval: A Benchmark System with a Comprehensive Evaluation Model for Federated Learning

1 code implementation19 Nov 2020 Di Chai, Leye Wang, Kai Chen, Qiang Yang

As an innovative solution for privacy-preserving machine learning (ML), federated learning (FL) is attracting much attention from research and industry areas.

Federated Learning

Gaussian Processes with Skewed Laplace Spectral Mixture Kernels for Long-term Forecasting

no code implementations8 Nov 2020 Kai Chen, Twan van Laarhoven, Elena Marchiori

The heavy tail and skewness characteristics of such distributions in the spectral domain allow to capture long-range covariance of the signal in the time domain.

Gaussian Processes Time Series

Possible multi-orbital ground state in CeCu$_2$Si$_2$

no code implementations5 Oct 2020 Andrea Amorese, Andrea Marino, Martin Sundermann, Kai Chen, Zhiwei Hu, Thomas Willers, Fadi Choukani, Philippe Ohresser, Javier Herrero-Martin, Stefano Agrestini, Chien-Te Chen, Hong-Ji Lin, Maurits W. Haverkort, Silvia Seiro, Christoph Geibel, Frank Steglich, Liu Hao Tjeng, Gertrud Zwicknagl, Andrea Severing

The crystal-field ground state wave function of CeCu$_2$Si$_2$ has been investigated with linear polarized $M$-edge x-ray absorption spectroscopy from 250mK to 250K, thus covering the superconducting ($T_{\text{c}}$=0. 6K), the Kondo ($T_{\text{K}}$$\approx$20K) as well as the Curie-Weiss regime.

Strongly Correlated Electrons

Exploring the Generalizability of Spatio-Temporal Traffic Prediction: Meta-Modeling and an Analytic Framework

1 code implementation20 Sep 2020 Leye Wang, Di Chai, Xuanzhe Liu, Liyue Chen, Kai Chen

The Spatio-Temporal Traffic Prediction (STTP) problem is a classical problem with plenty of prior research efforts that benefit from traditional statistical learning and recent deep learning approaches.

Traffic Prediction

Domain-specific Communication Optimization for Distributed DNN Training

no code implementations16 Aug 2020 Hao Wang, Jingrong Chen, Xinchen Wan, Han Tian, Jiacheng Xia, Gaoxiong Zeng, Weiyan Wang, Kai Chen, Wei Bai, Junchen Jiang

Communication overhead poses an important obstacle to distributed DNN training and draws increasing attention in recent years.

FPGA-Based Hardware Accelerator of Homomorphic Encryption for Efficient Federated Learning

no code implementations21 Jul 2020 Zhaoxiong Yang, Shuihai Hu, Kai Chen

Our framework implements the representative Paillier homomorphic cryptosystem with high level synthesis for flexibility and portability, with careful optimization on the modular multiplication operation in terms of processing clock cycle, resource usage and clock frequency.

Federated Learning

DS-Sync: Addressing Network Bottlenecks with Divide-and-Shuffle Synchronization for Distributed DNN Training

no code implementations7 Jul 2020 Weiyan Wang, Cengguang Zhang, Liu Yang, Kai Chen, Kun Tan

However, due to the global synchronization nature, its performance can be significantly influenced by network bottlenecks caused by either static topology heterogeneity or dynamic bandwidth contentions.

Nonlinear Residual Echo Suppression Based on Multi-stream Conv-TasNet

1 code implementation15 May 2020 Hongsheng Chen, Teng Xiang, Kai Chen, Jing Lu

Acoustic echo cannot be entirely removed by linear adaptive filters due to the nonlinear relationship between the echo and far-end signal.

Acoustic echo cancellation

Neural Data-to-Text Generation with Dynamic Content Planning

no code implementations16 Apr 2020 Kai Chen, Fayuan Li, Baotian Hu, Weihua Peng, Qingcai Chen, Hong Yu

We further design a reconstruction mechanism with a novel objective function that can reconstruct the whole entry of the used data sequentially from the hidden states of the decoder, which aids the accuracy of the generated text.

Data-to-Text Generation

Feature Pyramid Grids

1 code implementation7 Apr 2020 Kai Chen, Yuhang Cao, Chen Change Loy, Dahua Lin, Christoph Feichtenhofer

Feature pyramid networks have been widely adopted in the object detection literature to improve feature representations for better handling of variations in scale.

Neural Architecture Search Object Detection +1

Vanishing Point Guided Natural Image Stitching

no code implementations6 Apr 2020 Kai Chen, Jian Yao, Jingmin Tu, Yahui Liu, Yinxuan Li, Li Li

Recently, works on improving the naturalness of stitching images gain more and more extensive attention.

Image Stitching

Quantifying the Performance of Federated Transfer Learning

no code implementations30 Dec 2019 Qinghe Jing, Weiyan Wang, Junxue Zhang, Han Tian, Kai Chen

The scarcity of data and isolated data islands encourage different organizations to share data with each other to train machine learning models.

Transfer Learning

Unified Approach to Witness Nonentanglement-Breaking Quantum Channels

no code implementations23 Dec 2019 Yi-Zheng Zhen, Yingqiu Mao, Kai Chen, Francesco Buscemi, Oscar Dahlsten

The ability of quantum devices to preserve or distribute entanglement is essential in employing quantum technologies.

Quantum Physics

Side-Aware Boundary Localization for More Precise Object Detection

1 code implementation ECCV 2020 Jiaqi Wang, Wenwei Zhang, Yuhang Cao, Kai Chen, Jiangmiao Pang, Tao Gong, Jianping Shi, Chen Change Loy, Dahua Lin

To tackle the difficulty of precise localization in the presence of displacements with large variance, we further propose a two-step localization scheme, which first predicts a range of movement through bucket prediction and then pinpoints the precise position within the predicted bucket.

Object Detection

Towards Security Threats of Deep Learning Systems: A Survey

no code implementations28 Nov 2019 Yingzhe He, Guozhu Meng, Kai Chen, Xingbo Hu, Jinwen He

In order to unveil the security weaknesses and aid in the development of a robust deep learning system, we undertake an investigation on attacks towards deep learning, and analyze these attacks to conclude some findings in multiple views.

Adversarial Attack Model extraction

Gliding vertex on the horizontal bounding box for multi-oriented object detection

1 code implementation21 Nov 2019 Yongchao Xu, Mingtao Fu, Qimeng Wang, Yukang Wang, Kai Chen, Gui-Song Xia, Xiang Bai

Yet, the widely adopted horizontal bounding box representation is not appropriate for ubiquitous oriented objects such as objects in aerial images and scene texts.

Object Detection In Aerial Images Pedestrian Detection +1

Real-time Scene Text Detection with Differentiable Binarization

11 code implementations20 Nov 2019 Minghui Liao, Zhaoyi Wan, Cong Yao, Kai Chen, Xiang Bai

Recently, segmentation-based methods are quite popular in scene text detection, as the segmentation results can more accurately describe scene text of various shapes such as curve text.

Ranked #5 on Scene Text Detection on SCUT-CTW1500 (F-Measure metric)

Binarization Optical Character Recognition +1

Interpretable Encrypted Searchable Neural Networks

no code implementations14 Aug 2019 Kai Chen, Zhongrui Lin, Jian Wan, Chungen Xu

In cloud security, traditional searchable encryption (SE) requires high computation and communication overhead for dynamic search and update.

Multi-owner Secure Encrypted Search Using Searching Adversarial Networks

no code implementations7 Aug 2019 Kai Chen, Zhongrui Lin, Jian Wan, Lei Xu, Chungen Xu

To address this, this paper proposes secure and efficient multi-keyword ranked search over encrypted cloud data for multi-owner model based on searching adversarial networks.

Distributed Computing

Secure Federated Matrix Factorization

no code implementations12 Jun 2019 Di Chai, Leye Wang, Kai Chen, Qiang Yang

The key principle of federated learning is training a machine learning model without needing to know each user's personal raw private data.

Federated Learning

Extracting Symptoms and their Status from Clinical Conversations

no code implementations ACL 2019 Nan Du, Kai Chen, Anjuli Kannan, Linh Tran, Yu-Hui Chen, Izhak Shafran

This paper describes novel models tailored for a new application, that of extracting the symptoms mentioned in clinical conversations along with their status.

CARAFE: Content-Aware ReAssembly of FEatures

2 code implementations ICCV 2019 Jiaqi Wang, Kai Chen, Rui Xu, Ziwei Liu, Chen Change Loy, Dahua Lin

CARAFE introduces little computational overhead and can be readily integrated into modern network architectures.

Instance Segmentation Object Detection +1

Prime Sample Attention in Object Detection

1 code implementation CVPR 2020 Yuhang Cao, Kai Chen, Chen Change Loy, Dahua Lin

Our experiments demonstrate that it is often more effective to focus on prime samples than hard samples when training a detector.

Object Detection

Libra R-CNN: Towards Balanced Learning for Object Detection

5 code implementations CVPR 2019 Jiangmiao Pang, Kai Chen, Jianping Shi, Huajun Feng, Wanli Ouyang, Dahua Lin

In this work, we carefully revisit the standard training practice of detectors, and find that the detection performance is often limited by the imbalance during the training process, which generally consists in three levels - sample level, feature level, and objective level.

Object Detection

Hybrid Task Cascade for Instance Segmentation

5 code implementations CVPR 2019 Kai Chen, Jiangmiao Pang, Jiaqi Wang, Yu Xiong, Xiaoxiao Li, Shuyang Sun, Wansen Feng, Ziwei Liu, Jianping Shi, Wanli Ouyang, Chen Change Loy, Dahua Lin

In exploring a more effective approach, we find that the key to a successful instance segmentation cascade is to fully leverage the reciprocal relationship between detection and segmentation.

Instance Segmentation Object Detection +1

Region Proposal by Guided Anchoring

2 code implementations CVPR 2019 Jiaqi Wang, Kai Chen, Shuo Yang, Chen Change Loy, Dahua Lin

State-of-the-art detectors mostly rely on a dense anchoring scheme, where anchors are sampled uniformly over the spatial domain with a predefined set of scales and aspect ratios.

Object Detection Region Proposal

Seeing isn't Believing: Practical Adversarial Attack Against Object Detectors

no code implementations26 Dec 2018 Yue Zhao, Hong Zhu, Ruigang Liang, Qintao Shen, Shengzhi Zhang, Kai Chen

In this paper, we presented systematic solutions to build robust and practical AEs against real world object detectors.

Adversarial Attack Autonomous Driving

Generalized Content-Preserving Warps for Image Stitching

no code implementations18 Sep 2018 Kai Chen, Jingmin Tu, Jian Yao

Content-Preserving Warping (CPW) is a typical method to deal with this issue, in which geometric and photometric constraints are imposed to guide the warping process.

Image Stitching

Multiple Combined Constraints for Image Stitching

no code implementations18 Sep 2018 Kai Chen, Jingmin Tu, Binbin Xiang, Li Li, Jian Yao

In this paper, geometric and photometric constraints are combined to improve the alignment quality, which is based on the observation that these two kinds of constraints are complementary.

Image Stitching

Double Supervised Network with Attention Mechanism for Scene Text Recognition

no code implementations2 Aug 2018 Yuting Gao, Zheng Huang, Yuchen Dai, Cheng Xu, Kai Chen, Jie Tuo

In this paper, we propose Double Supervised Network with Attention Mechanism (DSAN), a novel end-to-end trainable framework for scene text recognition.

Scene Text Recognition

Novel Compressible Adaptive Spectral Mixture Kernels for Gaussian Processes with Sparse Time and Phase Delay Structures

no code implementations1 Aug 2018 Kai Chen, Yijue Dai, Feng Yin, Elena Marchiori, Sergios Theodoridis

By verifying the presence of dependencies between function components using Gaussian conditionals and posterior covariance, we first propose a new SM kernel variant with a time and phase delay dependency structure (SMD) and then provide a structure adaptation (SA) algorithm for the SMD.

Gaussian Processes Model Compression

Optimizing Video Object Detection via a Scale-Time Lattice

1 code implementation CVPR 2018 Kai Chen, Jiaqi Wang, Shuo Yang, Xingcheng Zhang, Yuanjun Xiong, Chen Change Loy, Dahua Lin

High-performance object detection relies on expensive convolutional networks to compute features, often leading to significant challenges in applications, e. g. those that require detecting objects from video streams in real time.

Video Object Detection

Understanding Membership Inferences on Well-Generalized Learning Models

1 code implementation13 Feb 2018 Yunhui Long, Vincent Bindschaedler, Lei Wang, Diyue Bu, Xiao-Feng Wang, Haixu Tang, Carl A. Gunter, Kai Chen

Membership Inference Attack (MIA) determines the presence of a record in a machine learning model's training data by querying the model.

Inference Attack Membership Inference Attack

CommanderSong: A Systematic Approach for Practical Adversarial Voice Recognition

no code implementations24 Jan 2018 Xuejing Yuan, Yuxuan Chen, Yue Zhao, Yunhui Long, Xiaokang Liu, Kai Chen, Shengzhi Zhang, Heqing Huang, Xiao-Feng Wang, Carl A. Gunter

For this purpose, we developed novel techniques that address a key technical challenge: integrating the commands into a song in a way that can be effectively recognized by ASR through the air, in the presence of background noise, while not being detected by a human listener.

Automatic Speech Recognition

Understanding Android Obfuscation Techniques: A Large-Scale Investigation in the Wild

no code implementations5 Jan 2018 Shuaike Dong, Menghao Li, Wenrui Diao, Xiangyu Liu, Jian Liu, Zhou Li, Fenghao Xu, Kai Chen, Xiao-Feng Wang, Kehuan Zhang

In this paper, we seek to better understand Android obfuscation and depict a holistic view of the usage of obfuscation through a large-scale investigation in the wild.

Cryptography and Security

Fused Text Segmentation Networks for Multi-oriented Scene Text Detection

no code implementations11 Sep 2017 Yuchen Dai, Zheng Huang, Yuting Gao, Youxuan Xu, Kai Chen, Jie Guo, Weidong Qiu

In this paper, we introduce a novel end-end framework for multi-oriented scene text detection from an instance-aware semantic segmentation perspective.

Multi-Oriented Scene Text Detection Object Detection +3

Video Object Segmentation with Re-identification

3 code implementations1 Aug 2017 Xiaoxiao Li, Yuankai Qi, Zhe Wang, Kai Chen, Ziwei Liu, Jianping Shi, Ping Luo, Xiaoou Tang, Chen Change Loy

Specifically, our Video Object Segmentation with Re-identification (VS-ReID) model includes a mask propagation module and a ReID module.

Semantic Segmentation Video Object Segmentation +2

Discover and Learn New Objects from Documentaries

1 code implementation CVPR 2017 Kai Chen, Hang Song, Chen Change Loy, Dahua Lin

Despite the remarkable progress in recent years, detecting objects in a new context remains a challenging task.

Convolutional Neural Networks for Page Segmentation of Historical Document Images

no code implementations5 Apr 2017 Kai Chen, Mathias Seuret

This paper presents a Convolutional Neural Network (CNN) based page segmentation method for handwritten historical document images.

Convolutional Regression for Visual Tracking

no code implementations14 Nov 2016 Kai Chen, Wenbing Tao

In this paper, we propose a Convolutional Regression framework for visual tracking (CRT).

Visual Object Tracking Visual Tracking

Context-aware System Service Call-oriented Symbolic Execution of Android Framework with Application to Exploit Generation

no code implementations2 Nov 2016 Lannan Luo, Qiang Zeng, Chen Cao, Kai Chen, Jian Liu, Limin Liu, Neng Gao, Min Yang, Xinyu Xing, Peng Liu

We present novel ideas and techniques to resolve the challenges, and have built the first system for symbolic execution of Android Framework.

Cryptography and Security Software Engineering

A Novel Scene Text Detection Algorithm Based On Convolutional Neural Network

no code implementations7 Apr 2016 Xiaohang Ren, Kai Chen, Jun Sun

In this paper, we propose a CNN based scene text detection algorithm with a new text region extractor.

Scene Text Detection

A CNN Based Scene Chinese Text Recognition Algorithm With Synthetic Data Engine

no code implementations7 Apr 2016 Xiaohang Ren, Kai Chen, Jun Sun

The proposed Chinese text recognition algorithm is evaluated with two Chinese text datasets.

Scene Text Recognition

Distributed Representations of Words and Phrases and their Compositionality

40 code implementations NeurIPS 2013 Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg Corrado, Jeffrey Dean

Motivated by this example, we present a simple method for finding phrases in text, and show that learning good vector representations for millions of phrases is possible.

Efficient Estimation of Word Representations in Vector Space

70 code implementations16 Jan 2013 Tomas Mikolov, Kai Chen, Greg Corrado, Jeffrey Dean

We propose two novel model architectures for computing continuous vector representations of words from very large data sets.

Word Similarity

Large Scale Distributed Deep Networks

no code implementations NeurIPS 2012 Jeffrey Dean, Greg Corrado, Rajat Monga, Kai Chen, Matthieu Devin, Mark Mao, Marc'Aurelio Ranzato, Andrew Senior, Paul Tucker, Ke Yang, Quoc V. Le, Andrew Y. Ng

Recent work in unsupervised feature learning and deep learning has shown that being able to train large models can dramatically improve performance.

Object Recognition Speech Recognition

Improved Successive Cancellation Decoding of Polar Codes

1 code implementation17 Aug 2012 Kai Chen, Kai Niu, Jia-Ru Lin

As improved versions of successive cancellation (SC) decoding algorithm, successive cancellation list (SCL) decoding and successive cancellation stack (SCS) decoding are used to improve the finite-length performance of polar codes.

Information Theory Information Theory

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