检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Wan, Ruosi Xiong, Haoyi Li, Xingjian Zhu, Zhanxing Huan, Jun Big Data Laboratory Baidu Inc. Beijing China National Engineering Laboratory for Deep Learning Technology and Applications Beijing China School of Mathematical Sciences Peking University Beijing China

—Transfer learning have been frequently used to improve deep neural network training through incorporating weights of pre-trained networks as the starting-point of optimization for regularization. While deep transfer learning can usually boost the performance with better accuracy and faster convergence, transferring weights from inappropriate networks hurts training procedure and may lead to even lower accuracy. In this paper, we consider deep transfer learning as minimizing a linear combination of empirical loss and regularizer based on pre-trained weights, where the regularizer would restrict the training procedure from lowering the empirical loss, with conflicted descent directions (e.g., derivatives). Following the view, we propose a novel strategy making regularization-based deep Transfer learning Never Hurt (DTNH) that, for each iteration of training procedure, computes the derivatives of the two terms separately, then re-estimates a new descent direction that does not hurt the empirical loss minimization while preserving the regularization affects from the pre-trained weights. Extensive experiments have been done using common transfer learning regularizers, such as L2-SP and knowledge distillation, on top of a wide range of deep transfer learning benchmarks including Caltech, MIT indoor 67, CIFAR-10 and ImageNet. The empirical results show that the proposed descent direction estimation strategy DTNH can always improve the performance of deep transfer learning tasks based on all above regularizers, even when transferring pre-trained weights from inappropriate networks. All in all, DTNH strategy can improve state-of-the-art regularizers in all cases with 0.1%—7% higher accuracy in all experiments. Copyright © 2019, The Authors. All rights reserved.

关键词： deep neural networks

来源：评论

学校读者我要写书评

暂无评论

GINet: Graph interaction network for scene parsing

arXiv

引用

arXiv 2020年

作者： Wu, Tianyi Lu, Yu Zhu, Yu Zhang, Chuang Wu, Ming Ma, Zhanyu Guo, Guodong Institute of Deep Learning Baidu Research Beijing China National Engineering Laboratory for Deep Learning Technology and Application Beijing China Beijing University of Posts and Telecommunications Beijing China

Recently, context reasoning using image regions beyond local convolution has shown great potential for scene parsing. In this work, we explore how to incorperate the linguistic knowledge to promote context reasoning over image regions by proposing a Graph Interaction unit (GI unit) and a Semantic Context Loss (SC-loss). The GI unit is capable of enhancing feature representations of convolution networks over high-level semantics and learning the semantic coherency adaptively to each sample. Specifically, the dataset-based linguistic knowledge is first incorporated in the GI unit to promote context reasoning over the visual graph, then the evolved representations of the visual graph are mapped to each local representation to enhance the discriminated capability for scene parsing. GI unit is further improved by the SC-loss to enhance the semantic representations over the exemplar-based semantic graph. We perform full ablation studies to demonstrate the effectiveness of each component in our approach. Particularly, the proposed GINet outperforms the state-of-the-art approaches on the popular benchmarks, including Pascal-Context and COCO Stuff. Copyright © 2020, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Large scale autonomous driving scenarios clustering with self-supervised feature extraction

arXiv

引用

arXiv 2021年

作者： Zhao, Jinxin Fang, Jin Ye, Zhixian Zhang, Liangjun Baidu Research and National Engineering Laboratory of Deep Learning Technology and Application China Baidu Research United States

The clustering of autonomous driving scenario data can substantially benefit the autonomous driving validation and simulation systems by improving the simulation tests' completeness and fidelity. This article proposes a comprehensive data clustering framework for a large set of vehicle driving data. Existing algorithms utilize handcrafted features whose quality relies on the judgments of human experts. Additionally, the related feature compression methods are not scalable for a large data-set. Our approach thoroughly considers the traffic elements, including both in-traffic agent objects and map information. Meanwhile, we proposed a self-supervised deep learning approach for spatial and temporal feature extraction to avoid biased data representation. With the newly designed driving data clustering evaluation metrics based on data-augmentation, the accuracy assessment does not require a human-labeled dataset, which is subject to human bias. Via such unprejudiced evaluation metrics, we have shown our approach surpasses the existing methods that rely on handcrafted feature extractions. © 2021, CC BY-NC-SA.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Dynamic Group Transformer: A General Vision Transformer Backbone with Dynamic Group Attention

arXiv

引用

arXiv 2022年

作者： Liu, Kai Wu, Tianyi Liu, Cong Guo, Guodong Sun Yat-Sen University Guangzhou China Institute of Deep Learning Baidu Research Beijing China National Engineering Laboratory for Deep Learning Technology and Application Beijing China

Recently, Transformers have shown promising performance in various vision tasks. To reduce the quadratic computation complexity caused by each query attending to all keys/values, various methods have constrained the range of attention within local regions, where each query only attends to keys/values within a hand-crafted window. However, these hand-crafted window partition mechanisms are data-agnostic and ignore their input content, so it is likely that one query maybe attends to irrelevant keys/values. To address this issue, we propose a Dynamic Group Attention (DG-Attention), which dynamically divides all queries into multiple groups and selects the most relevant keys/values for each group. Our DG-Attention can flexibly model more relevant dependencies without any spatial constraint that is used in hand-crafted window based attention. Built on the DG-Attention, we develop a general vision transformer backbone named Dynamic Group Transformer (DGT). Extensive experiments show that our models can outperform the state-of-the-art methods on multiple common vision tasks, including image classification, semantic segmentation, object detection, and instance segmentation. Copyright © 2022, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LAE : Long-Tailed Age Estimation 19th

LAE : Long-Tailed Age Estimation

引用

19th International Conference on Computer Analysis of Images and Patterns, CAIP 2021

作者： Bao, Zenghao Tan, Zichang Zhu, Yu Wan, Jun Ma, Xibo Lei, Zhen Guo, Guodong CBSR&NLPR Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science and Innovation Chinese Academy of Sciences Beijing China Institute of Deep Learning Baidu Research Beijing China National Engineering Laboratory for Deep Learning Technology and Application Beijing China

ISBN: (纸本)9783030891305

Facial age estimation is an important yet very challenging problem in computer vision. To improve the performance of facial age estimation, we first formulate a simple standard baseline and build a much strong one by collecting the tricks in pre-training, data augmentation, model architecture, and so on. Compared with the standard baseline, the proposed one significantly decreases the estimation errors. Moreover, long-tailed recognition has been an important topic in facial age datasets, where the samples often lack on the elderly and children. To train a balanced age estimator, we propose a two-stage training method named Long-tailed Age Estimation (LAE), which decouples the learning procedure into representation learning and classification. The effectiveness of our approach has been demonstrated on the dataset provided by organizers of Guess The Age Contest 2021. © 2021, Springer Nature Switzerland AG.

关键词： deep learning

来源：评论

学校读者我要写书评

暂无评论

Anti-UAV: A Large Multi-Modal Benchmark for UAV Tracking

arXiv

引用

arXiv 2021年

作者： Jiang, Nan Wang, Kuiran Peng, Xiaoke Yu, Xuehui Wang, Qiang Xing, Junliang Li, Guorong Zhao, Jian Guo, Guodong Han, Zhenjun Beijing101408 China Beijing China Institute of North Electronic Equipment Beijing China Institute of Deep Learning Baidu Research and National Engineering Laboratory for Deep Learning Technology and Application China

Unmanned Aerial Vehicle (UAV) offers lots of applications in both commerce and recreation. Therefore, perception of the status of UAVs is crucially important. In this paper, we consider the task of tracking UAVs, providing rich information such as location and trajectory. To facilitate research on this topic, we introduce a new benchmark, referred to as Anti-UAV, opening up a promising direction for UAV tracking in a long distance with more than 300 video pairs containing over 580k manually annotated bounding boxes. Furthermore, the advancement of addressing research challenges in Anti-UAV can help the design of anti-UAV systems, leading to better surveillance of UAVs. Accordingly, a simple yet effective approach named dual-flow semantic consistency (DFSC) is proposed for UAV tracking. Modulated by the semantic flow across video sequences, the tracker learns more robust class-level semantic information and obtains more discriminative instance-level features. Experiments show the significant performance gain of our proposed approach over state-of-the-art trackers, and the challenging aspects of Anti-UAV. The Anti-UAV benchmark and the code of the proposed approach will be publicly available at https://***/ucas-vg/Anti-UAV. Copyright © 2021, The Authors. All rights reserved.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

RotPredictor: Unsupervised Canonical Viewpoint learning for Point Cloud Classification

RotPredictor: Unsupervised Canonical Viewpoint Learning for ...

引用

International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission (3DIMPVT)

作者： Jin Fang Dingfu Zhou Xibin Song Shengze Jin Ruigang Yang Liangjun Zhang Baidu Research National Engineering Laboratory of Deep Learning Technology and Application China ETH Zürich Switzerland University of Kentucky

ISBN: (数字)9781728181288

ISBN: (纸本)9781728181295

Recently, significant progress has been achieved in analyzing the 3D point cloud with deep learning techniques. However, existing networks suffer from poor generalization and robustness to arbitrary rotations applied to the input point cloud. Different from traditional strategies that improve the rotation robustness with data augmentation or specifically designed spherical representation or harmonics-based kernels, we propose to rotate the point cloud into a canonical viewpoint for boosting the following downstream target task, e.g., object classification and part segmentation. Specifically, the canonical viewpoint is predicted by the network RotPredictor in an unsupervised way and the loss function is only built on the target task. Our RotPredictor satisfies the rotation equivariance property in (3) approximately and the predication output has the linear relationship with the applied rotation transformation. In addition, the RotPredictor is an independent plug and play module, which can be employed by any point-based deep learning framework without extra burden. Experimental results on the public model classification dataset ModelNet40 show the performance for all baselines can be boosted by integrating the proposed module. In addition, by adding our proposed module, we can achieve the state-of-the-art classification accuracy with 90.2% on the rotation-augmented ModelNet40 benchmark.

关键词： Three-dimensional displays Task analysis Robustness Convolution Two dimensional displays deep learning Solid modeling

来源：评论

学校读者我要写书评

暂无评论

Relaxed 2-D principal component analysis by Lpnorm for face recognition

arXiv

引用

arXiv 2019年

作者： Chen, Xiao Jia, Zhi-Gang Cai, Yunfeng Zhao, Mei-Xiang School of Mathematics and Statistics Jiangsu Key Laboratory of Education Big Data Science and Engineering Jiangsu Normal University Xuzhou221116 China Baidu Research National Engineering Laboratory for Deep Learning Technology and Applications Beijing100193 China

A relaxed two dimensional principal component analysis (R2DPCA) approach is proposed for face recognition. Different to the 2DPCA, 2DPCA-L1 and G2DPCA, the R2DPCA utilizes the label information (if known) of training samples to calculate a relaxation vector and presents a weight to each subset of training data. A new relaxed scatter matrix is defined and the computed projection axes are able to increase the accuracy of face recognition. The optimal Lp-norms are selected in a reasonable range. Numerical experiments on practical face databased indicate that the R2DPCA has high generalization ability and can achieve a higher recognition rate than state-of-the-art methods. Copyright © 2019, The Authors. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Revisiting distillation and incremental classifier learning

arXiv

引用

arXiv 2018年

作者： Javed, Khurram Shafait, Faisal Deep Learning Laboratory National Center of Artificial Intelligence Islamabad Pakistan School of Electrical Engineering and Computer Science National University of Sciences and Technology

One of the key differences between the learning mechanism of humans and Artificial Neural Networks (ANNs) is the ability of humans to learn one task at a time. ANNs, on the other hand, can only learn multiple tasks simultaneously. Any attempts at learning new tasks incrementally cause them to completely forget about previous tasks. This lack of ability to learn incrementally, called Catastrophic Forgetting, is considered a major hurdle in building a true AI system. In this paper, our goal is to isolate the truly effective existing ideas for incremental learning from those that only work under certain condi- tions. To this end, we first thoroughly analyze the current state of the art (iCaRL) method for incremental learning and demonstrate that the good performance of the system is not because of the reasons presented in the existing literature. We conclude that the success of iCaRL is primarily due to knowledge distillation and recognize a key limitation of knowledge distillation, i.e, it often leads to bias in classifiers. Finally, we propose a dynamic threshold moving algorithm that is able to success- fully remove this bias. We demonstrate the effectiveness of our algorithm on CIFAR100 and MNIST datasets showing near-optimal results. Our implementation is available at : https://***/Khurramjaved96/ incremental-learning. Copyright © 2018, The Authors. All rights reserved.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Pale Transformer: A General Vision Transformer Backbone with Pale-Shaped Attention

arXiv

引用

arXiv 2021年

作者： Wu, Sitong Wu, Tianyi Tan, Haoru Guo, Guodong Institute of Deep Learning Baidu Research Beijing China National Engineering Laboratory for Deep Learning Technology and Application Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China

Recently, Transformers have shown promising performance in various vision tasks. To reduce the quadratic computation complexity caused by the global self-attention, various methods constrain the range of attention within a local region to improve its efficiency. Consequently, their receptive fields in a single attention layer are not large enough, resulting in insufficient context modeling. To address this issue, we propose a Pale-Shaped self-Attention (PS-Attention), which performs self-attention within a pale-shaped region. Compared to the global self-attention, PS-Attention can reduce the computation and memory costs significantly. Meanwhile, it can capture richer contextual information under the similar computation complexity with previous local self-attention mechanisms. Based on the PS-Attention, we develop a general Vision Transformer backbone with a hierarchical architecture, named Pale Transformer, which achieves 83.4%, 84.3%, and 84.9% Top-1 accuracy with the model size of 22M, 48M, and 85M respectively for 224 × 224 ImageNet-1K classification, outperforming the previous Vision Transformer backbones. For downstream tasks, our Pale Transformer backbone performs better than the recent state-of-the-art CSWin Transformer by a large margin on ADE20K semantic segmentation and COCO object detection & instance segmentation. The code will be released on https://***/BRIDL/PaddleViT. © 2021, CC BY.

关键词： Instance Segmentation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：