检索结果-内蒙古大学图书馆

Multi-Modal Face Presentation Attack Detection 1

学校读者我要写书评

暂无评论

丛书名： Synthesis Lectures on Computer Vision

1000年

作者： Jun Wan Guodong Guo Sergio Escalera Hugo Jair Escalante Stan Z. Li

Bayesian Optimized 1-Bit CNNs

学校读者我要写书评

暂无评论

Bayesian Optimized 1-Bit CNNs

International Conference on Computer Vision (ICCV)

作者： Jiaxin Gu Junhe Zhao Xiaolong Jiang Baochang Zhang Jianzhuang Liu Guodong Guo Rongrong Ji Beihang University Beijing China Institute of Deep Learning Baidu Research Beijing China National Engineering Laboratory for Deep Learning Technology and Application Huawei Noah’s Ark Lab China School of Information Science and Engineering Xiamen University Fujian China Peng Cheng Lab Shenzhen China

ISBN: (数字)9781728148038

ISBN: (纸本)9781728148045

deep convolutional neural networks (DCNNs) have dominated the recent developments in computer vision through making various record-breaking models. However, it is still a great challenge to achieve powerful DCNNs in resource-limited environments, such as on embedded devices and smart phones. researchers have realized that 1-bit CNNs can be one feasible solution to resolve the issue; however, they are baffled by the inferior performance compared to the full-precision DCNNs. In this paper, we propose a novel approach, called Bayesian optimized 1-bit CNNs (denoted as BONNs), taking the advantage of Bayesian learning, a well-established strategy for hard problems, to significantly improve the performance of extreme 1-bit CNNs. We incorporate the prior distributions of full-precision kernels and features into the Bayesian framework to construct 1-bit CNNs in an end-to-end manner, which have not been considered in any previous related methods. The Bayesian losses are achieved with a theoretical support to optimize the network simultaneously in both continuous and discrete spaces, aggregating different losses jointly to improve the model capacity. Extensive experiments on the ImageNet and CIFAR datasets show that BONNs achieve the best classification performance compared to state-of-the-art 1-bit CNNs.

关键词： Bayes methods Kernel Quantization (signal) Convolution Training Frequency modulation Indexes

Invisible for both Camera and LiDAR: Security of multi-sensor fusion based perception in autonomous driving under physical-world attacks

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Cao, Yulong Wang, Ningfei Xiao, Chaowei Yang, Dawei Fang, Jin Yang, Ruigang Chen, Qi Alfred Liu, Mingyan Li, Bo University of California Irvine United States University of Michigan United States NVIDIA Research Arizona State University Inceptio Baidu Research and National Engineering Laboratory of Deep Learning Technology and Application China University of Illinois at Urbana-Champaign

In Autonomous Driving (AD) systems, perception is both security and safety critical. Despite various prior studies on its security issues, all of them only consider attacks on camera- or LiDAR-based AD perception alone. However, production AD systems today predominantly adopt a Multi-Sensor Fusion (MSF) based design, which in principle can be more robust against these attacks under the assumption that not all fusion sources are (or can be) attacked at the same time. In this paper, we present the first study of security issues of MSF-based perception in AD systems. We directly challenge the basic MSF design assumption above by exploring the possibility of attacking all fusion sources simultaneously. This allows us for the first time to understand how much security guarantee MSF can fundamentally provide as a general defense strategy for AD perception. We formulate the attack as an optimization problem to generate a physically-realizable, adversarial 3D-printed object that misleads an AD system to fail in detecting it and thus crash into it. To systematically generate such a physical-world attack, we propose a novel attack pipeline that addresses two main design challenges: (1) non-differentiable target camera and LiDAR sensing systems, and (2) non-differentiable cell-level aggregated features popularly used in LiDAR-based AD perception. We evaluate our attack on MSF algorithms included in representative open-source industry-grade AD systems in real-world driving scenarios. Our results show that the attack achieves over 90% success rate across different object types and MSF algorithms. Our attack is also found stealthy, robust to victim positions, transferable across MSF algorithms, and physical-world realizable after being 3D-printed and captured by LiDAR and camera devices. To concretely assess the end-to-end safety impact, we further perform simulation evaluation and show that it can cause a 100% vehicle collision rate for an industry-grade AD system. We also evalu

关键词： Autonomous vehicles

Bayesian optimized 1-Bit CNNs

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Gu, Jiaxin Zhao, Junhe Jiang, Xiaolong Zhang, Baochang Liu, Jianzhuang Guo, Guodong Ji, Rongrong Beihang University Beijing China Institute of Deep Learning Baidu Research Beijing China National Engineering Laboratory for Deep Learning Technology and Application Huawei Noah's Ark Lab China School of Information Science and Engineering Xiamen University Fujian China Peng Cheng Lab Shenzhen China

deep convolutional neural networks (DCNNs) have dominated the recent developments in computer vision through making various record-breaking models. However, it is still a great challenge to achieve powerful DCNNs in resource-limited environments, such as on embedded devices and smart phones. researchers have realized that 1-bit CNNs can be one feasible solution to resolve the issue;however, they are baffled by the inferior performance compared to the full-precision DCNNs. In this paper, we propose a novel approach, called Bayesian optimized 1-bit CNNs (denoted as BONNs), taking the advantage of Bayesian learning, a well-established strategy for hard problems, to significantly improve the performance of extreme 1-bit CNNs. We incorporate the prior distributions of full-precision kernels and features into the Bayesian framework to construct 1-bit CNNs in an end-to-end manner, which have not been considered in any previous related methods. The Bayesian losses are achieved with a theoretical support to optimize the network simultaneously in both continuous and discrete spaces, aggregating different losses jointly to improve the model capacity. Extensive experiments on the ImageNet and CIFAR datasets show that BONNs achieve the best classification performance compared to state-of-the-art 1-bit CNNs. Copyright © 2019, The Authors. All rights reserved.

关键词： deep neural networks

ProposalContrast: Unsupervised Pre-training for LiDAR-based 3D Object Detection

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Yin, Junbo Zhou, Dingfu Zhang, Liangjun Fang, Jin Xu, Cheng-Zhong Shen, Jianbing Wang, Wenguan School of Computer Science Beijing Institute of Technology China Baidu Research China National Engineering Laboratory of Deep Learning Technology and Application China SKL-IOTSC CIS University of Macau China ReLER AAII University of Technology Sydney Australia

Existing approaches for unsupervised point cloud pre-training are constrained to either scene-level or point/voxel-level instance discrimination. Scene-level methods tend to lose local details that are crucial for recognizing the road objects, while point/voxel-level methods inherently suffer from limited receptive field that is incapable of perceiving large objects or context environments. Considering region-level representations are more suitable for 3D object detection, we devise a new unsupervised point cloud pre-training framework, called ProposalContrast, that learns robust 3D representations by contrasting region proposals. Specifically, with an exhaustive set of region proposals sampled from each point cloud, geometric point relations within each proposal are modeled for creating expressive proposal representations. To better accommodate 3D detection properties, ProposalContrast optimizes with both inter-cluster and inter-proposal separation, i.e., sharpening the discriminativeness of proposal representations across semantic classes and object instances. The generalizability and transferability of ProposalContrast are verified on various 3D detectors (i.e., PV-RCNN, CenterPoint, PointPillars and PointRCNN) and datasets (i.e., KITTI, Waymo and ONCE). Copyright © 2022, The Authors. All rights reserved.

关键词： Object detection

ApolloCar3D: A Large 3D Car Instance Understanding Benchmark for Autonomous Driving

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Song, Xibin Wang, Peng Zhou, Dingfu Zhu, Rui Guan, Chenye Dai, Yuchao Su, Hao Li, Hongdong Yang, Ruigang Baidu Research National Engineering Laboratory of Deep Learning Technology and Application China University of California San Diego United States Northwestern Polytechnical University Xi’an China Australian National University Australia Australian Centre for Robotic Vision Australia

Autonomous driving has attracted remarkable attention from both industry and academia. An important task is to estimate 3D properties (e.g. translation, rotation and shape) of a moving or parked vehicle on the road. This task, while critical, is still under-researched in the computer vision community – partially owing to the lack of large scale and fully-annotated 3D car database suitable for autonomous driving research. In this paper, we contribute the first large-scale database suitable for 3D car instance understanding – ApolloCar3D. The dataset contains 5,277 driving images and over 60K car instances, where each car is fitted with an industry-grade 3D CAD model with absolute model size and semantically labelled keypoints. This dataset is above 20× larger than PASCAL3D+ [65] and KITTI [21], the current state-of-the-art. To enable efficient labelling in 3D, we build a pipeline by considering 2D-3D keypoint correspondences for a single instance and 3D relationship among multiple instances. Equipped with such dataset, we build various baseline algorithms with the state-of-the-art deep convolutional neural networks. Specifically, we first segment each car with a pre-trained Mask R-CNN [22], and then regress towards its 3D pose and shape based on a deformable 3D car model with or without using semantic keypoints. We show that using keypoints significantly improves fitting performance. Finally, we develop a new 3D metric jointly considering 3D pose and 3D shape, allowing for comprehensive evaluation and ablation study. By comparing with human performance we suggest several future directions for further improvements. Copyright © 2018, The Authors. All rights reserved.

关键词： Autonomous vehicles

Channel Attention Based Iterative Residual learning for Depth Map Super-Resolution

学校读者我要写书评

暂无评论

Channel Attention Based Iterative Residual Learning for Dept...

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Xibin Song Yuchao Dai Dingfu Zhou Liu Liu Wei Li Hongdong Li Ruigang Yang Baidu Research National Engineering Laboratory of Deep Learning Technology and Application China Northwestern Polytechnical University China Australian National University Australia Australian Centre for Robotic Vision Australia Shandong University China University of Kentucky Kentucky USA

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

Despite the remarkable progresses made in deep learning based depth map super-resolution (DSR), how to tackle real-world degradation in low-resolution (LR) depth maps remains a major challenge. Existing DSR model is generally trained and tested on synthetic dataset, which is very different from what would get from a real depth sensor. In this paper, we argue that DSR models trained under this setting are restrictive and not effective in dealing with realworld DSR tasks. We make two contributions in tackling real-world degradation of different depth sensors. First, we propose to classify the generation of LR depth maps into two types: non-linear downsampling with noise and interval downsampling, for which DSR models are learned correspondingly. Second, we propose a new framework for real-world DSR, which consists of four modules : 1) An iterative residual learning module with deep supervision to learn effective high-frequency components of depth maps in a coarse-to-fine manner; 2) A channel attention strategy to enhance channels with abundant high-frequency components; 3) A multi-stage fusion module to effectively reexploit the results in the coarse-to-fine process; and 4) A depth refinement module to improve the depth map by TGV regularization and input loss. Extensive experiments on benchmarking datasets demonstrate the superiority of our method over current state-of-the-art DSR methods.

关键词： Degradation Iron Color Kernel Image resolution Three-dimensional displays Feature extraction

Semi-supervised 3D Object Detection with Proficient Teachers

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Yin, Junbo Fang, Jin Zhou, Dingfu Zhang, Liangjun Xu, Cheng-Zhong Shen, Jianbing Wang, Wenguan School of Computer Science Beijing Institute of Technology China Baidu Research United States National Engineering Laboratory of Deep Learning Technology and Application China SKL-IOTSC Cis University of Macau China ReLER Aaii University of Technology Sydney Australia

Dominated point cloud-based 3D object detectors in autonomous driving scenarios rely heavily on the huge amount of accurately labeled samples, however, 3D annotation in the point cloud is extremely tedious, expensive and time-consuming. To reduce the dependence on large supervision, semi-supervised learning (SSL) based approaches have been proposed. The Pseudo-Labeling methodology is commonly used for SSL frameworks, however, the low-quality predictions from the teacher model have seriously limited its performance. In this work, we propose a new Pseudo-Labeling framework for semi-supervised 3D object detection, by enhancing the teacher model to a proficient one with several necessary designs. First, to improve the recall of pseudo labels, a Spatial-temporal Ensemble (STE) module is proposed to generate sufficient seed boxes. Second, to improve the precision of recalled boxes, a Clustering-based Box Voting (CBV) module is designed to get aggregated votes from the clustered seed boxes. This also eliminates the necessity of sophisticated thresholds to select pseudo labels. Furthermore, to reduce the negative influence of wrongly pseudo-labeled samples during the training, a soft supervision signal is proposed by considering Box-wise Contrastive learning (BCL). The effectiveness of our model is verified on both ONCE and Waymo datasets. For example, on ONCE, our approach significantly improves the baseline by 9.51 mAP. Moreover, with half annotations, our model outperforms the oracle model with full annotations on Waymo. Copyright © 2022, The Authors. All rights reserved.

关键词： Object detection

deep Feedforward Sequential Memory Networks Based Mispronunciation Detection for Tibetan Students' Mandarin 2

学校读者我要写书评

暂无评论

Deep Feedforward Sequential Memory Networks Based Mispronunc...

2nd International Conference on Information Science and Education, ICISE-IE 2021

作者： Gan, Zhenye Zhao, Tianqin Yu, Xinke Yang, Hongwu College of Physics and Electronic Engineering Northwest Normal University Engineering Research Center of Gansu Province for Intelligent Information Technology and Application LanZhou China School of Educational Technology Northwest Normal University National and Local Joint Engineering Laboratory for Learning Analytics Technology of Internet Education Data LanZhou China

ISBN: (纸本)9781665438292

Computer assisted pronunciation training system (CAPT) can detect the wrong pronunciation produced by nonnative speakers and provide positive feedback. CAPT is helpful to improve the pronunciation level for L2 learners' accurately. Tibetan students' Mandarin is influenced by their native language pronunciation habits. So, this feature leads to their pronunciation being obviously different from that of standard mandarin. This paper used CNN model as a fundamental, and we introduced acoustic model: DFSMN and CTC. This acoustic model implemented a method of speech recognition on Tibetan students' mandarin mispronunciation detection. In order to continue improving the detection performance, we used extended initial final (XIF) as bias primitives and design 64 bias types. Experiment results show that the proposed method in this paper can effectively detect mispronunciation and provide correct feedback, with the DA of 88.02%, FRR of 7.95% and FAR of 25.74%. © 2021 IEEE

关键词： Students