检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Zhou, Nan Chen, Jiaxin Huang, Di State Key Laboratory of Software Development Environment Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China Hangzhou Innovation Institute Beihang University Hangzhou China

The visual models pretrained on large-scale benchmarks encode general knowledge and prove effective in building more powerful representations for downstream tasks. Most existing approaches follow the fine-tuning paradigm, either by initializing or regularizing the downstream model based on the pretrained one. The former fails to retain the knowledge in the successive fine-tuning phase, thereby prone to be over-fitting, and the latter imposes strong constraints to the weights or feature maps of the downstream model without considering semantic drift, often incurring insufficient optimization. To deal with these issues, we propose a novel fine-tuning framework, namely distribution regularization with semantic calibration (DR-Tune). It employs distribution regularization by enforcing the downstream task head to decrease its classification error on the pretrained feature distribution, which prevents it from over-fitting while enabling sufficient training of downstream encoders. Furthermore, to alleviate the interference by semantic drift, we develop the semantic calibration (SC) module to align the global shape and class centers of the pretrained and downstream feature distributions. Extensive experiments on widely used image classification datasets show that DR-Tune consistently improves the performance when combing with various backbones under different pretraining strategies. Code is availab.e at: https://***/weeknan/DR-Tune. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

OcTr: Octree-Based Transformer for 3D Object Detection

OcTr: Octree-Based Transformer for 3D Object Detection

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Chao Zhou Yanan Zhang Jiaxin Chen Di Huang State Key Laboratory of Software Development Environment Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China Hangzhou Innovation Institute Beihang University Hangzhou China

A key challenge for LiDAR-based 3D object detection is to capture sufficient features from large scale 3D scenes especially for distant or/and occluded objects. Albeit recent efforts made by Transformers with the long sequence modeling capability, they fail to properly balance the accuracy and efficiency, suffering from inadequate receptive fields or coarse-grained holistic correlations. In this paper, we propose an Octree-based Transformer, named OcTr, to address this issue. It first constructs a dynamic octree on the hierarchical feature pyramid through conducting self-attention on the top level and then recursively propagates to the level below restricted by the octants, which captures rich global context in a coarse-to-fine manner while maintaining the computational complexity under control. Furthermore, for enhanced foreground perception, we propose a hybrid positional embedding, composed of the semantic-aware positional embedding and attention mask, to fully exploit semantic and geometry clues. Extensive experiments are conducted on the Waymo Open Dataset and KITTI Dataset, and OcTr reaches newly state-of-the-art results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptive Sparse Convolutional Networks with Global Context Enhancement for Faster Object Detection on Drone Images

Adaptive Sparse Convolutional Networks with Global Context E...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Bowei Du Yecheng Huang Jiaxin Chen Di Huang State Key Laboratory of Software Development Environment Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China Hangzhou Innovation Institute Beihang University Hangzhou China

Object detection on drone images with low-latency is an important but challenging task on the resource-constrained unmanned aerial vehicle (UAV) platform. This paper investigates optimizing the detection head based on the sparse convolution, which proves effective in balancing the accuracy and efficiency. Nevertheless, it suffers from inadequate integration of contextual information of tiny objects as well as clumsy control of the mask ratio in the presence of foreground with varying scales. To address the issues above, we propose a novel global context-enhanced adaptive sparse convolutional network (CEASC). It first develops a context-enhanced group normalization (CE-GN) layer, by replacing the statistics based on sparsely sampled features with the global contextual ones, and then designs an adaptive multi-layer masking strategy to generate optimal mask ratios at distinct scales for compact foreground coverage, promoting both the accuracy and efficiency. Extensive experimental results on two major benchmarks, i.e. VisDrone and UAVDT, demonstrate that CEASC remarkably reduces the GFLOPs and accelerates the inference procedure when plugging into the typical state-of-the-art detection frameworks (e.g. RetinaNet and GFL V1) with competitive performance. Code is availab.e at https://***/Cuogeihong/CEASC.

关键词：

来源：评论

学校读者我要写书评

暂无评论

OcTr: Octree-based Transformer for 3D Object Detection

arXiv

引用

arXiv 2023年

作者： Zhou, Chao Zhang, Yanan Chen, Jiaxin Huang, Di State Key Laboratory of Software Development Environment Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China Hangzhou Innovation Institute Beihang University Hangzhou China

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Simple Image-level Classification Improves Open-vocabulary Object Detection

arXiv

引用

arXiv 2023年

作者： Fang, Ruohuan Pang, Guansong Bai, Xiao School of Computer Science and Engineering Beihang University China School of Computing and Information Systems Singapore Management University Singapore State Key Laboratory of Software Development Environment Jiangxi Research Institute Beihang University China

Open-Vocabulary Object Detection (OVOD) aims to detect novel objects beyond a given set of base categories on which the detection model is trained. Recent OVOD methods focus on adapting the image-level pre-trained vision-language models (VLMs), such as CLIP, to a region-level object detection task via, e.g., region-level knowledge distillation, regional prompt learning, or region-text pre-training, to expand the detection vocabulary. These methods have demonstrated remarkable performance in recognizing regional visual concepts, but they are weak in exploiting the VLMs' powerful global scene understanding ability learned from the billion-scale image-level text descriptions. This limits their capability in detecting hard objects of small, blurred, or occluded appearance from novel/base categories, whose detection heavily relies on contextual information. To address this, we propose a novel approach, namely Simple Image-level Classification for Context-Aware Detection Scoring (SIC-CADS), to leverage the superior global knowledge yielded from CLIP for complementing the current OVOD models from a global perspective. The core of SIC-CADS is a multi-modal multi-lab.l recognition (MLR) module that learns the object co-occurrence-based contextual information from CLIP to recognize all possible object categories in the scene. These image-level MLR scores can then be utilized to refine the instance-level detection scores of the current OVOD models in detecting those hard objects. This is verified by extensive empirical results on two popular benchmarks, OV-LVIS and OV-COCO, which show that SIC-CADS achieves significant and consistent improvement when combined with different types of OVOD models. Further, SIC-CADS also improves the cross-dataset generalization ability on Objects365 and OpenImages. Code is availab.e at https://***/mala-lab.SIC-CADS. Copyright © 2023, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

DR-Tune: Improving Fine-tuning of Pretrained Visual Models by Distribution Regularization with Semantic Calibration

DR-Tune: Improving Fine-tuning of Pretrained Visual Models b...

引用

International Conference on computer Vision (ICCV)

作者： Nan Zhou Jiaxin Chen Di Huang State Key Laboratory of Software Development Environment Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China Hangzhou Innovation Institute Beihang University Hangzhou China

关键词：

来源：评论

学校读者我要写书评

暂无评论

Character, Word, or Both? Revisiting the Segmentation Granularity for Chinese Pre-trained Language Models

arXiv

引用

arXiv 2023年

作者： Liang, Xinnian Zhou, Zefan Huang, Hui Wu, Shuangzhi Xiao, Tong Yang, Muyun Li, Zhoujun Bian, Chao State Key Lab of Software Development Environment Beihang University Beijing China School of Computer Science and Engineering Northeastern University Shenyang China Faculty of Computing Harbin Institute of Technology Harbin China Lark Platform Engineering-AI Beijing China

Pretrained language models (PLMs) have shown marvelous improvements across various NLP tasks. Most Chinese PLMs simply treat an input text as a sequence of characters, and completely ignore word information. Although Whole Word Masking can alleviate this, the semantics in words is still not well represented. In this paper, we revisit the segmentation granularity of Chinese PLMs. We propose a mixed-granularity Chinese BERT (MigBERT) by considering both characters and words. To achieve this, we design objective functions for learning both character and word-level representations. We conduct extensive experiments on various Chinese NLP tasks to evaluate existing PLMs as well as the proposed MigBERT. Experimental results show that MigBERT achieves new SOTA performance on all these tasks. Further analysis demonstrates that words are semantically richer than characters. More interestingly, we show that MigBERT also works with Japanese. Our code has been released here 1 and you can download our model here 2 © 2023, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

The Power of Age-based Reward in Fresh Information Acquisition

The Power of Age-based Reward in Fresh Information Acquisiti...

引用

IEEE Annual Joint Conference: INFOCOM, IEEE computer and Communications Societies

作者： Zhiyuan Wang Qingkai Meng Shan Zhang Hongbin Luo School of Computer Science and Engineering Beihang University Beijing China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Institute of Artificial Intelligence Beihang University Beijing China State Key Laboratory of Software Development Environment

Many Internet platforms collect fresh information of various points of interest (PoIs) relying on users who happen to be nearby the PoIs. The platform will offer reward to incentivize users and compensate their costs incurred from information acquisition. In practice, the user cost (and its distribution) is hidden to the platform, thus it is challenging to determine the optimal reward. In this paper, we investigate how the platform dynamically rewards the users, aiming to jointly reduce the age of information (AoI) and the operational expenditure (OpEx). Due to the hidden cost distribution, this is an online non-convex learning problem with partial feedback. To overcome the challenge, we first design an age-based rewarding scheme, which decouples the OpEx from the unknown cost distribution and enables the platform to accurately control its OpEx. We then take advantage of the age-based rewarding scheme and propose an exponentially discretizing and learning (EDAL) policy for platform operation. We prove that the EDAL policy performs asymptotically as well as the optimal decision (derived based on the cost distribution). Simulation results show that the age-based rewarding scheme protects the platform’s OpEx from the influence of the user characteristics, and verify the asymptotic optimality of the EDAL policy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Load-Aware Hierarchical Information-Centric Routing for Large-Scale LEO Satellite Networks

Load-Aware Hierarchical Information-Centric Routing for Larg...

引用

IEEE Conference on Wireless Communications and Networking

作者： Fei Yan Zhiyuan Wang Shan Zhang Qingkai Meng Hongbin Luo School of Computer Science and Engineering Beihang University Beijing China Zhongguancun Laboratory Beijing China State Key Laboratory of Virtual Reality Technology and Systems Beijing China State Key Laboratory of Software Development Environment Beijing China Institute of Artificial Intelligence Beihang University Beijing China

ISBN: (数字)9798350303582

ISBN: (纸本)9798350303599

The emerging large-scale low earth orbit (LEO) constellation is expected to provide global Internet services. However, large-scale satellite networks meet the challenges of topology dynamics and continuous traffic variation. This paper proposes LoHi, a Load-aware Hierarchical Information-centric (LoHi) Routing Protocol based on constellation Partitioning and logic path identifier (PID), to address the above challenges. Specifically, LoHi divides a constellation into satellite groups and only keeps track of the inter-satellite link (ISL) state within each group instead of the entire constellation, stabilizing global routing. Moreover, LoHi adopts the PID to denote the logic connectivity of adjacent satellite groups, which corresponds to multiple physical ISLs. Accordingly, the hierarchical multipath routing is calculated based on the inner-group and inter-group connectivity information. Furthermore, LoHi adjusts forwarding decisions according to the real-time traffic load on the ISL and group-level inter-group paths to reduce packet drop and queuing delay in a hierarchical pattern. Packet-level experiment results show that LoHi achieves a higher packet delivery ratio than the state-of-the-art mechanisms (up to 132.12%).

关键词： Satellites Web and internet services Low earth orbit satellites Telecommunication traffic Routing Throughput Routing protocols

来源：评论

学校读者我要写书评

暂无评论

SWin: A Set-Window Division Mechanism to Alleviate I/O Jitters of NVMe SSD Drives

SWin: A Set-Window Division Mechanism to Alleviate I/O Jitte...

引用

IEEE International Conference on High Performance Computing and Communications (HPCC)

作者： Yuting Liu Liang Wang Jinbin Zhu Runnan Shen Shixuan Jiang Limin Xiao State Key Laboratory of Software Development Environment Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China

NVMe SSDs increase the performance of I/O system significantly, but they still suffer from the problem of performance jitters. Although existing studies adopt optimized GC or schedulers to make up for the vulnerabilities, they cannot provide a near “GC-free” performance under various scenarios. In this paper, we propose SWin, a Set-Window division mechanism to alleviate I/O jitters of NVMe SSDs, in which we build an optimized scheduler with cache management on sets. First, we first divide NVMe SSD into set level and determine time windows based on sets. Then, an efficient I/O scheduler is designed to process requests of applications. Finally, we develop a host cache management strategy to ensure a stable response time for I/O requests. The experimental results indicate that the OCSSD system integrated with SWin can gain performance improvement by 32%, 34% and 14% in completion time, IOPS and latency performance, respectively.

关键词： Smart cities Scheduling algorithms Jitter Time factors

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：