检索结果-内蒙古大学图书馆

GBCNs: Genetic Binary Convolutional Networks for enhancing the performance of 1-bit DCNNs

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Liu, Chunlei W., Ding Y., Hu B., Zhang J., Liu G., Guo School of Electronic and Information Engineering Beihang University Unmanned System Research Institute Beihang University School of Automation Science and Electrical Engineering Beihang University Shenzhen Institutes of Advanced Technology University of Chinese Academy of Sciences Institute of Deep Learning Baidu Research National Engineering Laboratory for Deep Learning Technology and Application

Training 1-bit deep convolutional neural networks (DCNNs) is one of the most challenging problems in computer vision, because it is much easier to get trapped into local minima than conventional DCNNs. The reason lies in that the binarized kernels and activations of 1-bit DCNNs cause a significant accuracy loss and training inefficiency. To address this problem, we propose Genetic Binary Convolutional Networks (GBCNs) to optimize 1-bit DCNNs, by introducing a new balanced Genetic Algorithm (BGA) to improve the representational ability in an end-to-end framework. The BGA method is proposed to modify the binary process of GBCNs to alleviate the local minima problem, which can significantly improve the performance of 1-bit DCNNs. We develop a new BGA module that is generic and flexible, and can be easily incorporated into existing DCNNs, such as WideResNets and ResNets. Extensive experiments on the object classification tasks (CIFAR, ImageNet) validate the effectiveness of the proposed method. To highlight, our method shows strong generalization on the object recognition task, i.e., face recognition, facial and person re-identification. Copyright © 2019, The Authors. All rights reserved.

关键词： deep neural networks

Self-supervised Monocular Depth Estimation for All Day Images using Domain Separation

学校读者我要写书评

暂无评论

Self-supervised Monocular Depth Estimation for All Day Image...

International Conference on Computer Vision (ICCV)

作者： Lina Liu Xibin Song Mengmeng Wang Yong Liu Liangjun Zhang Institute of Cyber-Systems and Control Zhejiang University China Baidu Research China National Engineering Laboratory of Deep Learning Technology and Application China Huzhou Institue of Zhejiang University China

ISBN: (纸本)9781665428132

Remarkable results have been achieved by DCNN based self-supervised depth estimation approaches. However, most of these approaches can only handle either day-time or night-time images, while their performance degrades for all-day images due to large domain shift and the variation of illumination between day and night images. To relieve these limitations, we propose a domain-separated network for self-supervised depth estimation of all-day images. Specifically, to relieve the negative influence of disturbing terms (illumination, etc.), we partition the information of day and night image pairs into two complementary sub-spaces: private and invariant domains, where the former contains the unique information (illumination, etc.) of day and night images and the latter contains essential shared information (texture, etc.). Meanwhile, to guarantee that the day and night images contain the same information, the domain-separated network takes the day-time images and corresponding night-time images (generated by GAN) as input, and the private and invariant feature extractors are learned by orthogonality and similarity loss, where the domain gap can be alleviated, thus better depth maps can be expected. Meanwhile, the reconstruction and photometric losses are utilized to estimate complementary information and depth maps effectively. Experimental results demonstrate that our approach achieves state-of-the-art depth estimation results for all-day images on the challenging Oxford RobotCar dataset, proving the superiority of our proposed approach. Code and data split are available at https://***/LINA-lln/ADDS-DepthNet.

关键词： Computer vision Codes Estimation Lighting Generative adversarial networks Feature extraction Data mining

Self-supervised monocular depth estimation for all day images using domain separation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Liu, Lina Song, Xibin Wang, Mengmeng Liu, Yong Zhang, Liangjun Institute of Cyber-Systems and Control Zhejiang University China Baidu Research China Huzhou Institue of Zhejiang University China National Engineering Laboratory of Deep Learning Technology and Application China

关键词： Textures

iffDetector: Inference-aware feature filtering for object detection

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Mao, Mingyuan Tian, Yuxin Zhang, Baochang Ye, Qixiang Liu, Wanquan Guo, Guodong Doermann, David Beihang University Beijing China University of Chinese Academy of Sciences Beijing China Curtin University Perth Australia Institute of Deep Learning Baidu Research Beijing China National Engineering Laboratory for Deep Learning Technology and Application University at Buffalo Buffalo United States

Modern CNN-based object detectors focus on feature configuration during training but often ignore feature optimization during inference. In this paper, we propose a new feature optimization approach to enhance features and suppress background noise in both the training and inference stages. We introduce a generic Inference-aware Feature Filtering (IFF) module that can easily be combined with modern detectors, resulting in our iffDetector. Unlike conventional open-loop feature calculation approaches without feedback, the IFF module performs closed-loop optimization by leveraging high-level semantics to enhance the convolutional features. By applying Fourier transform analysis, we demonstrate that the IFF module acts as a negative feedback that theoretically guarantees the stability of feature learning. IFF can be fused with CNN-based object detectors in a plug-and-play manner with negligible computational cost overhead. Experiments on the PASCAL VOC and MS COCO datasets demonstrate that our iffDetector consistently outperforms state-of-the-art methods by significant margins1. Copyright © 2020, The Authors. All rights reserved.

关键词： Object detection

Bi-level Doubly Variational learning for Energy-based Latent Variable Models

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Kan, Ge Lü, Jinhu Wang, Tian Zhang, Baochang Zhu, Aichun Huang, Lei Guo, Guodong Snoussi, Hichem School of Automation Science and Electrical Engineering Institue of Artificial Intelligence Beihang University Beijing China School of Computer Science and Technology Nanjing Tech University Nanjing China Institute of Deep Learning Baidu Research National Engineering Laboratory for Deep Learning Technology and Application Beijing China University of Technology of Troyes Troyes France

Energy-based latent variable models (EBLVMs) are more expressive than conventional energy-based models. However, its potential on visual tasks are limited by its training process based on maximum likelihood estimate that requires sampling from two intractable distributions. In this paper, we propose Bi-level doubly variational learning (BiDVL), which is based on a new bi-level optimization framework and two tractable variational distributions to facilitate learning EBLVMs. Particularly, we lead a decoupled EBLVM consisting of a marginal energy-based distribution and a structural posterior to handle the difficulties when learning deep EBLVMs on images. By choosing a symmetric KL divergence in the lower level of our framework, a compact BiDVL for visual tasks can be obtained. Our model achieves impressive image generation performance over related works. It also demonstrates the significant capacity of testing image reconstruction and out-of-distribution detection. Copyright © 2022, The Authors. All rights reserved.

关键词： Vision

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

IoU loss for 2D/3D object detection

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Zhou, Dingfu Fang, Jin Song, Xibin Guan, Chenye Yin, Junbo Dai, Yuchao Yang, Ruigang Baidu Research National Engineering Laboratory of Deep Learning Technology and Application China Beijing Lab of Intelligent Information Technology School of Computer Science Beijing Institute of Technology China Northwestern Polytechnical University Xi'an China

In 2D/3D object detection task, Intersection-over-Union (IoU) has been widely employed as an evaluation metric to evaluate the performance of different detectors in the testing stage. However, during the training stage, the common distance loss (e.g., L1 or L2) is often adopted as the loss function to minimize the discrepency between the predicted and ground truth Bounding Box (Bbox). To eliminate the performance gap between training and testing, the IoU loss has been introduced for 2D object detection in [1] and [2]. Unfortunately, all these approaches only work for axis-aligned 2D Bboxes, which cannot be applied for more general object detection task with rotated Bboxes. To resolve this issue, we investigate the IoU computation for two rotated Bboxes first and then implement a unified framework, IoU loss layer for both 2D and 3D object detection tasks. By integrating the implemented IoU loss into several state-of-the-art 3D object detectors, consistent improvements have been achieved for both bird-eye-view 2D detection and point cloud 3D detection on the public KITTI [3] benchmark. Copyright © 2019, The Authors. All rights reserved.

关键词： Object recognition

Enhancing person-Job fit for talent recruitment: An ability-aware neural network approach

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Qin, Chuan Zhu, Hengshu Xu, Tong Zhu, Chen Jiang, Liang Chen, Enhong Xiong, Hui Anhui Province Key Lab of Big Data Analysis and Application University of Science and Technology of China Baidu Talent Intelligence Center Baidu Inc Business Intelligence Lab Baidu Research National Engineering Laboratory of Deep Learning Technology an Application China

The wide spread use of online recruitment services has led to information explosion in the job market. As a result, the recruiters have to seek the intelligent ways for Person-Job Fit, which is the bridge for adapting the right job seekers to the right positions. Existing studies on Person-Job Fit have a focus on measuring the matching degree between the talent qualification and the job requirements mainly based on the manual inspection of human resource experts despite of the subjective, incomplete, and inefficient nature of the human judgement. To this end, in this paper, we propose a novel end-to-end Ability-aware Person-Job Fit Neural Network (APJFNN) model, which has a goal of reducing the dependence on manual labour and can provide better interpretation about the fitting results. The key idea is to exploit the rich information available at abundant historical job application data. Specifically, we propose a word-level semantic representation for both job requirements and job seekers’ experiences based on Recurrent Neural Network (RNN). Along this line, four hierarchical ability-aware attention strategies are designed to measure the different importance of job requirements for semantic representation, as well as measuring the different contribution of each job experience to a specific ability requirement. Finally, extensive experiments on a large-scale real-world data set clearly validate the effectiveness and interpretability of the APJFNN framework compared with several baselines. Copyright © 2018, The Authors. All rights reserved.

关键词： Recurrent neural networks

RBCN: Rectified Binary convolutional networks for enhancing the Performance of 1-bit DCNNs

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Liu, Chunlei Ding, Wenrui Xia, Xin Hu, Yuan Zhang, Baochang Liu, Jianzhuang Zhuang, Bohan Guo, Guodong School of Electronic and Information Engineering Beihang University Unmanned System Research Institute Beihang University School of Automation Science and Electrical Engineering Beihang University Huawei Noah's Ark Lab University of Adelaide Institute of Deep Learning Baidu Research National Engineering Laboratory for Deep Learning Technology and Application

Binarized convolutional neural networks (BCNNs) are widely used to improve memory and computation efficiency of deep convolutional neural networks (DCNNs) for mobile and AI chips based applications. However, current BCNNs are not able to fully explore their corresponding full-precision models, causing a significant performance gap between them. In this paper, we propose rectified binary convolutional networks (RBCNs), towards optimized BCNNs, by combining full-precision kernels and feature maps to rectify the binarization process in a unified framework. In particular, we use a GAN to train the 1-bit binary network with the guidance of its corresponding full-precision model, which significantly improves the performance of BCNNs. The rectified convolutional layers are generic and flexible, and can be easily incorporated into existing DCNNs such as WideResNets and ResNets. Extensive experiments demonstrate the superior performance of the proposed RBCNs over state-of-the-art BCNNs. In particular, our method shows strong generalization on the object tracking task. Copyright © 2019, The Authors. All rights reserved.

关键词： deep neural networks