no code implementations • 31 May 2023 • Zhongwei Wan, Che Liu, Mi Zhang, Jie Fu, Benyou Wang, Sibo Cheng, Lei Ma, César Quilodrán-Casas, Rossella Arcucci
Med-UniC reaches superior performance across 5 medical image tasks and 10 datasets encompassing over 30 diseases, offering a versatile framework for unifying multi-modal medical data within diverse linguistic communities.
no code implementations • 23 May 2023 • Manuel Kunz, Stefan Birr, Mones Raslan, Lei Ma, Zhen Li, Adele Gouttes, Mateusz Koren, Tofigh Naghibi, Johannes Stephan, Mariia Bulycheva, Matthias Grzeschik, Armin Kekić, Michael Narodovitch, Kashif Rasul, Julian Sieber, Tim Januschowski
These include the volume of data, the irregularity, the high amount of turn-over in the catalog and the fixed inventory assumption.
no code implementations • CVPR 2023 • Yang Hou, Qing Guo, Yihao Huang, Xiaofei Xie, Lei Ma, Jianjun Zhao
Second, we find that the statistical differences between natural and DeepFake images are positively associated with the distribution shifting between the two kinds of images, and we propose to use a distribution-aware loss to guide the optimization of different degradations.
no code implementations • 7 Apr 2023 • Lei Ma, Jingyang Zhang, Ke Deng, Peng Xue, Zhiming Cui, Yu Fang, Minhui Tang, Yue Zhao, Min Zhu, Zhongxiang Ding, Dinggang Shen
In this study, we develop an unbiased dental template by constructing an accurate dental atlas from CBCT images with guidance of teeth segmentation.
1 code implementation • 15 Mar 2023 • Yuguang Yang, Yu Pan, JingJing Yin, Jiangyu Han, Lei Ma, Heng Lu
SqueezeFormer has recently shown impressive performance in automatic speech recognition (ASR).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
no code implementations • 8 Mar 2023 • Peng Xue, Jingyang Zhang, Lei Ma, Mianxin Liu, Yuning Gu, Jiawei Huang, Feihong Liua, Yongsheng Pan, Xiaohuan Cao, Dinggang Shen
In addition, such paired organ segmentations are not always available in DCE-CT images due to the flow of contrast agents.
1 code implementation • 2 Mar 2023 • Da Song, Zhijie Wang, Yuheng Huang, Lei Ma, Tianyi Zhang
In this work, we propose DeepLens, an interactive system that helps users detect and explore OOD issues in massive text corpora.
1 code implementation • 2 Mar 2023 • Zhijie Wang, Yuheng Huang, Da Song, Lei Ma, Tianyi Zhang
The core of DeepSeer is a state abstraction method that bundles semantically similar hidden states in an RNN model and abstracts the model as a finite state machine.
no code implementations • 27 Jan 2023 • Zhuo Li, Derui Zhu, Yujing Hu, Xiaofei Xie, Lei Ma, Yan Zheng, Yan Song, Yingfeng Chen, Jianjun Zhao
Generally, episodic control-based approaches are solutions that leverage highly-rewarded past experiences to improve sample efficiency of DRL algorithms.
no code implementations • 13 Dec 2022 • Zhijie Wang, Yuheng Huang, Lei Ma, Haruki Yokoyama, Susumu Tokumoto, Kazuki Munakata
More importantly, it also lacks systematic investigation on how to perform the risk assessment for AI systems from unit level to system level.
1 code implementation • 3 Dec 2022 • Yinghua Li, Xueqi Dang, Haoye Tian, Tiezhu Sun, Zhijie Wang, Lei Ma, Jacques Klein, Tegawende F. Bissyande
In this paper, we conduct the most extensive empirical study on 56, 682 published AI apps from three perspectives: dataset characteristics, development issues, and user feedback and privacy.
no code implementations • 20 Nov 2022 • Zhongyu Fang, Aoyun He, Qihui Yu, Baopeng Gao, Weiping Ding, Tong Zhang, Lei Ma
In this paper, we developed a large multimodal emotion dataset, named "HED" dataset, to facilitate the emotion recognition task, and accordingly propose a multimodal emotion recognition method.
no code implementations • 12 Oct 2022 • Shuangzhi Li, Zhijie Wang, Felix Juefei-Xu, Qing Guo, Xingyu Li, Lei Ma
Then, for the first attempt, we construct a benchmark based on the physical-aware common corruptions for point cloud detectors, which contains a total of 1, 122, 150 examples covering 7, 481 scenes, 25 common corruption types, and 6 severities.
no code implementations • 3 Oct 2022 • Zhibo Liu, Yuanyuan Yuan, Shuai Wang, Xiaofei Xie, Lei Ma
BTD takes DNN executables and outputs full model specifications, including types of DNN operators, network topology, dimensions, and parameters that are (nearly) identical to those of the input models.
no code implementations • 21 Sep 2022 • Xuhong Ren, Jianlang Chen, Felix Juefei-Xu, Wanli Xue, Qing Guo, Lei Ma, Jianjun Zhao, ShengYong Chen
Then, we propose a novel core-failure-set guided DARTS that embeds a K-center-greedy algorithm for DARTS to select suitable corrupted failure examples to refine the model architecture.
no code implementations • 26 Aug 2022 • Jianing Li, Jiaming Liu, Xiaobao Wei, Jiyuan Zhang, Ming Lu, Lei Ma, Li Du, Tiejun Huang, Shanghang Zhang
In this paper, we propose a novel Uncertainty-Guided Depth Fusion (UGDF) framework to fuse the predictions of monocular and stereo depth estimation networks for spike camera.
1 code implementation • 22 Jul 2022 • Qiang Hu, Yuejun Guo, Xiaofei Xie, Maxime Cordy, Lei Ma, Mike Papadakis, Yves Le Traon
Recent studies show that test selection for DNN is a promising direction that tackles this issue by selecting minimal representative data to label and using these data to assess the model.
no code implementations • 14 Jun 2022 • Jingyang Zhang, Peng Xue, Ran Gu, Yuning Gu, Mianxin Liu, Yongsheng Pan, Zhiming Cui, Jiawei Huang, Lei Ma, Dinggang Shen
In clinical practice, a segmentation network is often required to continually learn on a sequential data stream from multiple sites rather than a consolidated set, due to the storage cost and privacy restriction.
no code implementations • 11 Jun 2022 • Qiang Hu, Yuejun Guo, Xiaofei Xie, Maxime Cordy, Lei Ma, Mike Papadakis, Yves Le Traon
Distribution shift has been a longstanding challenge for the reliable deployment of deep learning (DL) models due to unexpected accuracy degradation.
no code implementations • 24 Mar 2022 • Xiaofei Xie, Tianlin Li, Jian Wang, Lei Ma, Qing Guo, Felix Juefei-Xu, Yang Liu
Inspired by software testing, a number of structural coverage criteria are designed and proposed to measure the test adequacy of DNNs.
no code implementations • 23 Jan 2022 • Tiejun Huang, Yajing Zheng, Zhaofei Yu, Rui Chen, Yuan Li, Ruiqin Xiong, Lei Ma, Junwei Zhao, Siwei Dong, Lin Zhu, Jianing Li, Shanshan Jia, Yihua Fu, Boxin Shi, Si Wu, Yonghong Tian
By treating vidar as spike trains in biological vision, we have further developed a spiking neural network-based machine vision system that combines the speed of the machine and the mechanism of biological vision, achieving high-speed object detection and tracking 1, 000x faster than human vision.
1 code implementation • 7 Jan 2022 • Qing Guo, Jingyang Sun, Felix Juefei-Xu, Lei Ma, Di Lin, Wei Feng, Song Wang
First, we propose the uncertainty-aware cascaded predictive filtering (UC-PFilt) that can identify the difficulties of reconstructing clean pixels via predicted kernels and remove the residual rain traces effectively.
1 code implementation • 5 Jan 2022 • Amin Eslami Abyane, Derui Zhu, Roberto Souza, Lei Ma, Hadi Hemmati
Therefore, to better understand the current quality status and challenges of these SOTA FL techniques in the presence of attacks and faults, we perform a large-scale empirical study to investigate the SOTA FL's quality from multiple angles of attacks, simulated faults (via mutation operators), and aggregation (defense) methods.
no code implementations • 4 Jan 2022 • Liwen Hu, Lei Ma, Dawei Weng, Tiejun Huang
More importantly, due to mimicking receptive field mechanism to collect regional information, RVSM can filter high intensity noise effectively and improves the problem that Spike camera is sensitive to noise largely.
no code implementations • 26 Nov 2021 • Hua Qi, Zhijie Wang, Qing Guo, Jianlang Chen, Felix Juefei-Xu, Lei Ma, Jianjun Zhao
In this work, as the first attempt, we initiate to repair DNNs by jointly optimizing the architecture and weights at a higher (i. e., block) level.
no code implementations • 19 Nov 2021 • Yuheng Huang, Lei Ma, Yuanchun Li
Vision Transformer (ViT) is known to be highly nonlinear like other classical neural networks and could be easily fooled by both natural and adversarial patch perturbations.
1 code implementation • 4 Nov 2021 • Shangqing Liu, Xiaofei Xie, JingKai Siow, Lei Ma, Guozhu Meng, Yang Liu
Specifically, we propose to construct graphs for the source code and queries with bidirectional GGNN (BiGGNN) to capture the local structural information of the source code and queries.
1 code implementation • CVPR 2022 • Liwen Hu, Rui Zhao, Ziluo Ding, Lei Ma, Boxin Shi, Ruiqin Xiong, Tiejun Huang
Further, for training SCFlow, we synthesize two sets of optical flow data for the spiking camera, SPIkingly Flying Things and Photo-realistic High-speed Motion, denoted as SPIFT and PHM respectively, corresponding to random high-speed and well-designed scenes.
no code implementations • 7 Oct 2021 • Qin Liu, Han Deng, Chunfeng Lian, Xiaoyang Chen, Deqiang Xiao, Lei Ma, Xu Chen, Tianshu Kuang, Jaime Gateno, Pew-Thian Yap, James J. Xia
We propose a multi-stage coarse-to-fine CNN-based framework, called SkullEngine, for high-resolution segmentation and large-scale landmark detection through a collaborative, integrated, and scalable JSD model and three segmentation and landmark detection refinement models.
no code implementations • 11 Sep 2021 • Deqiang Xiao, Hannah Deng, Tianshu Kuang, Lei Ma, Qin Liu, Xu Chen, Chunfeng Lian, Yankun Lang, Daeseung Kim, Jaime Gateno, Steve Guofang Shen, Dinggang Shen, Pew-Thian Yap, James J. Xia
In the training stage, the simulator maps jaw deformities of a patient bone to a normal bone to generate a simulated deformed bone.
no code implementations • 28 Jul 2021 • Qing Guo, Zhijie Wang, Felix Juefei-Xu, Di Lin, Lei Ma, Wei Feng, Yang Liu
3D point cloud completion is very challenging because it heavily relies on the accurate understanding of the complex 3D shapes (e. g., high-curvature, concave/convex, and hollowed-out 3D shapes) and the unknown & diverse patterns of the partially available point clouds.
1 code implementation • ICCV 2021 • Qing Guo, Ziyi Cheng, Felix Juefei-Xu, Lei Ma, Xiaofei Xie, Yang Liu, Jianjun Zhao
In this work, we explore the robustness of visual object trackers against motion blur from a new angle, i. e., adversarial blur attack (ABA).
no code implementations • 14 Jul 2021 • Yihao Huang, Qing Guo, Felix Juefei-Xu, Lei Ma, Weikai Miao, Yang Liu, Geguang Pu
To this end, we first comprehensively investigate two kinds of pixel denoising methods for adversarial robustness enhancement (i. e., existing additive-based and unexplored filtering-based methods) under the loss functions of image-level and semantic-level, respectively, showing that pixel-wise filtering can obtain much higher image quality (e. g., higher PSNR) as well as higher robustness (e. g., higher accuracy on adversarial examples) than existing pixel-wise additive-based method.
no code implementations • 23 Apr 2021 • Ziyi Cheng, Xuhong Ren, Felix Juefei-Xu, Wanli Xue, Qing Guo, Lei Ma, Jianjun Zhao
Online updating of the object model via samples from historical frames is of great importance for accurate visual object tracking.
1 code implementation • 27 Feb 2021 • Felix Juefei-Xu, Run Wang, Yihao Huang, Qing Guo, Lei Ma, Yang Liu
To fill this gap, in this paper, we provide a comprehensive overview and detailed analysis of the research work on the topic of DeepFake generation, DeepFake detection as well as evasion of DeepFake detection, with more than 318 research papers carefully surveyed.
no code implementations • 1 Jan 2021 • Simin Chen, Zihe Song, Lei Ma, Cong Liu, Wei Yang
We first theoretically clarify under which condition AttackDist can provide a certified detecting performance, then show that a potential application of AttackDist is distinguishing zero-day adversarial examples without knowing the mechanisms of new attacks.
no code implementations • 1 Jan 2021 • Qing Guo, Felix Juefei-Xu, Changqing Zhou, Lei Ma, Xiaofei Xie, Wei Feng, Yang Liu
Moreover, comprehensive evaluations have demonstrated two important properties of our method: First, superior transferability across DNNs.
no code implementations • 19 Nov 2020 • Bing Yu, Hua Qi, Qing Guo, Felix Juefei-Xu, Xiaofei Xie, Lei Ma, Jianjun Zhao
In this paper, we propose a style-guided data augmentation for repairing DNN in the operational environment.
no code implementations • 16 Oct 2020 • Ruohua Shi, Wenyao Wang, Zhixuan Li, Liuyuan He, Kaiwen Sheng, Lei Ma, Kai Du, Tingting Jiang, Tiejun Huang
Computer vision technology is widely used in biological and medical data analysis and understanding.
2 code implementations • 19 Sep 2020 • Qing Guo, Jingyang Sun, Felix Juefei-Xu, Lei Ma, Xiaofei Xie, Wei Feng, Yang Liu
To fill this gap, in this paper, we regard the single-image deraining as a general image-enhancing problem and originally propose a model-free deraining method, i. e., EfficientDeRain, which is able to process a rainy image within 10~ms (i. e., around 6~ms on average), over 80 times faster than the state-of-the-art method (i. e., RCDNet), while achieving similar de-rain effects.
no code implementations • 19 Sep 2020 • Liming Zhai, Felix Juefei-Xu, Qing Guo, Xiaofei Xie, Lei Ma, Wei Feng, Shengchao Qin, Yang Liu
To defend the DNNs from the negative rain effect, we also present a defensive deraining strategy, for which we design an adversarial rain augmentation that uses mixed adversarial rain layers to enhance deraining models for downstream DNN perception.
no code implementations • 13 Jun 2020 • Hua Qi, Qing Guo, Felix Juefei-Xu, Xiaofei Xie, Lei Ma, Wei Feng, Yang Liu, Jianjun Zhao
As the GAN-based face image and video generation techniques, widely known as DeepFakes, have become more and more matured and realistic, there comes a pressing and urgent demand for effective DeepFakes detectors.
1 code implementation • 13 Jun 2020 • Yihao Huang, Felix Juefei-Xu, Run Wang, Qing Guo, Lei Ma, Xiaofei Xie, Jianwen Li, Weikai Miao, Yang Liu, Geguang Pu
At this moment, GAN-based image generation methods are still imperfect, whose upsampling design has limitations in leaving some certain artifact patterns in the synthesized image.
no code implementations • 11 Jun 2020 • Lei Ma, Ke Guan, Dong Yan, Danping He, Nuno R. Leonor, Bo Ai, Junhyeong Kim
In this paper, the satellite-terrestrial channel at 22. 6 GHz is characterized for a typical high-speed railway (HSR) environment.
1 code implementation • 19 May 2020 • Dongming Wei, Sahar Ahmad, Yunzhi Huang, Lei Ma, Zhengwang Wu, Gang Li, Li Wang, Qian Wang, Pew-Thian Yap, Dinggang Shen
Deformable image registration is fundamental to longitudinal and population analysis.
no code implementations • 14 May 2020 • Jianwen Sun, Tianwei Zhang, Xiaofei Xie, Lei Ma, Yan Zheng, Kangjie Chen, Yang Liu
Adversarial attacks against conventional Deep Learning (DL) systems and algorithms have been widely studied, and various defenses were proposed.
no code implementations • 24 Apr 2020 • Xiyue Zhang, Xiaofei Xie, Lei Ma, Xiaoning Du, Qiang Hu, Yang Liu, Jianjun Zhao, Meng Sun
Based on this, we propose an automated testing technique to generate multiple types of uncommon AEs and BEs that are largely missed by existing techniques.
no code implementations • 20 Feb 2020 • Shangwei Guo, Tianwei Zhang, Han Yu, Xiaofei Xie, Lei Ma, Tao Xiang, Yang Liu
It guarantees that each benign node in a decentralized system can train a correct model under very strong Byzantine attacks with an arbitrary number of faulty nodes.
1 code implementation • NeurIPS 2020 • Qing Guo, Felix Juefei-Xu, Xiaofei Xie, Lei Ma, Jian Wang, Bing Yu, Wei Feng, Yang Liu
Besides, the attack is further enhanced by adaptively tuning the translations of object and background.
no code implementations • 9 Dec 2019 • Run Wang, Felix Juefei-Xu, Qing Guo, Yihao Huang, Xiaofei Xie, Lei Ma, Yang Liu
In this paper, we investigate and introduce a new type of adversarial attack to evade FR systems by manipulating facial content, called \textbf{\underline{a}dversarial \underline{mor}phing \underline{a}ttack} (a. k. a.
1 code implementation • ECCV 2020 • Qing Guo, Xiaofei Xie, Felix Juefei-Xu, Lei Ma, Zhongguo Li, Wanli Xue, Wei Feng, Yang Liu
We identify that online object tracking poses two new challenges: 1) it is difficult to generate imperceptible perturbations that can transfer across frames, and 2) real-time trackers require the attack to satisfy a certain level of efficiency.
no code implementations • 15 Sep 2019 • Qianyu Guo, Sen Chen, Xiaofei Xie, Lei Ma, Qiang Hu, Hongtao Liu, Yang Liu, Jianjun Zhao, Xiaohong Li
However, the differences in architecture designs and implementations of existing frameworks and platforms bring new challenges for DL software development and deployment.
no code implementations • 13 Sep 2019 • Run Wang, Felix Juefei-Xu, Lei Ma, Xiaofei Xie, Yihao Huang, Jian Wang, Yang Liu
In recent years, generative adversarial networks (GANs) and its variants have achieved unprecedented success in image synthesis.
no code implementations • 19 Jun 2019 • Jie M. Zhang, Mark Harman, Lei Ma, Yang Liu
This paper provides a comprehensive survey of Machine Learning Testing (ML testing) research.
no code implementations • 10 Jan 2019 • Lei Ma, Hongliang Li, Qingbo Wu, Fanman Meng, King Ngi Ngan
Finally, we propose a hierarchy neighborhood discriminative hashing loss to unify the single-label and multilabel image retrieval problem with a one-stream deep neural network architecture.
no code implementations • 13 Dec 2018 • Xiaoning Du, Xiaofei Xie, Yi Li, Lei Ma, Jianjun Zhao, Yang Liu
Our in-depth evaluation on a state-of-the-art speech-to-text DL system demonstrates the effectiveness of our technique in improving quality and reliability of stateful DL systems.
no code implementations • 13 Nov 2018 • Qianyu Guo, Xiaofei Xie, Lei Ma, Qiang Hu, Ruitao Feng, Li Li, Yang Liu, Jianjun Zhao, Xiaohong Li
Up to the present, it still lacks a comprehensive study on how current diverse DL frameworks and platforms influence the DL software development process.
no code implementations • 10 Oct 2018 • Lei Ma, Felix Juefei-Xu, Minhui Xue, Qiang Hu, Sen Chen, Bo Li, Yang Liu, Jianjun Zhao, Jianxiong Yin, Simon See
Over the past decades, deep learning (DL) systems have achieved tremendous success and gained great popularity in various applications, such as intelligent machines, image processing, speech processing, and medical diagnostics.
no code implementations • 7 Sep 2018 • Alvin Chan, Lei Ma, Felix Juefei-Xu, Xiaofei Xie, Yang Liu, Yew Soon Ong
Deep neural networks (DNN), while becoming the driving force of many novel technology and achieving tremendous success in many cutting-edge applications, are still vulnerable to adversarial attacks.
no code implementations • 4 Sep 2018 • Xiaofei Xie, Lei Ma, Felix Juefei-Xu, Hongxu Chen, Minhui Xue, Bo Li, Yang Liu, Jianjun Zhao, Jianxiong Yin, Simon See
In company with the data explosion over the past decade, deep neural network (DNN) based software has experienced unprecedented leap and is becoming the key driving force of many novel industrial applications, including many safety-critical scenarios such as autonomous driving.
no code implementations • 20 Jun 2018 • Lei Ma, Fuyuan Zhang, Minhui Xue, Bo Li, Yang Liu, Jianjun Zhao, Yadong Wang
Deep learning (DL) has achieved remarkable progress over the past decade and been widely applied to many safety-critical applications.
no code implementations • 15 Jun 2018 • Jakub Breier, Xiaolu Hou, Dirmanto Jap, Lei Ma, Shivam Bhasin, Yang Liu
As deep learning systems are widely adopted in safety- and security-critical applications, such as autonomous vehicles, banking systems, etc., malicious faults and attacks become a tremendous concern, which potentially could lead to catastrophic consequences.
4 code implementations • 14 May 2018 • Lei Ma, Fuyuan Zhang, Jiyuan Sun, Minhui Xue, Bo Li, Felix Juefei-Xu, Chao Xie, Li Li, Yang Liu, Jianjun Zhao, Yadong Wang
To do this, by sharing the same spirit of mutation testing in traditional software, we first define a set of source-level mutation operators to inject faults to the source of DL (i. e., training data and training programs).
Software Engineering
no code implementations • 20 Mar 2018 • Lei Ma, Felix Juefei-Xu, Fuyuan Zhang, Jiyuan Sun, Minhui Xue, Bo Li, Chunyang Chen, Ting Su, Li Li, Yang Liu, Jianjun Zhao, Yadong Wang
Deep learning (DL) defines a new data-driven programming paradigm that constructs the internal system logic of a crafted neuron network through a set of training data.