检索结果-内蒙古大学图书馆

2022 IEEE International Conference on Multimedia and Expo, ICME 2022

作者： Cai, Jinmian Wang, Zheng Fu, Huazhu Chen, Jingjing Jiang, Yu-Gang School of Computer Science Fudan University Shanghai Key Lab of Intelligent Information Processing China Shanghai Collaborative Innovation Center on Intelligent Visual Computing China Biren Technology IHPC A-STAR

ISBN: (数字)9781665485630

ISBN: (纸本)9781665485630

Real-world data is often unbalanced and exhibits long-tailed distribution over classes. Vanilla classification models trained on imbalanced datasets inherently exhibit bias towards dominant classes. Existing debiasing methods mostly balance the data or the loss during training. Nevertheless, these data-acquiring methods are not suitable for situations where training data are unavailable. In this paper, we appeal to solutions without access to training data and propose a datafree debiasing (Free-D) method that serves as a plug-and-play module for any standard classification model. Specifically, our method adjusts both the feature representation via feature representation shifting and the classifier weight via class prior compensation in a data-free manner. We evaluate and compare our methods on four long-tailed visual recognition datasets, i.e., long-tailed CIFAR-10/-100, ImageNet-LT, and Places-LT. Extensive experiments demonstrate that the proposed data-free method achieves comparable results of other data-acquired methods. © 2022 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Retrieval Augmented Recipe Generation

Retrieval Augmented Recipe Generation

引用

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Guoshan Liu Hailong Yin Bin Zhu Jingjing Chen Chong-Wah Ngo Yu-Gang Jiang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai Collaborative Innovation Center on Intelligent Visual Computing Singapore Management University

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

The growing interest in generating recipes from food images has drawn substantial research attention in recent years. Existing works for recipe generation primarily utilize a two-stage training method—first predicting ingredients from a food image and then generating instructions from both the image and ingredients. Large Multi-modal Models (LMMs), which have achieved notable success across a variety of vision and language tasks, shed light on generating both ingredients and instructions directly from images. Nevertheless, LMMs still face the common issue of hallu-cinations during recipe generation, leading to suboptimal performance. To tackle this issue, we propose a retrieval augmented large multimodal model for recipe generation. We first introduce Stochastic Diversified Retrieval Augmentation (SDRA) to retrieve recipes semantically related to the image from an existing datastore as a supplement, integrating them into the prompt to add diverse and rich context to the input image. Additionally, Self-Consistency Ensemble Voting mechanism is proposed to determine the most confident prediction recipes as the final output. It calculates the consistency among generated recipe candidates, which use different retrieval recipes as context for generation. Extensive experiments validate the effectiveness of our proposed method, which demonstrates state-of-the-art (SOTA) performance in recipe generation on the Recipe1M dataset.

关键词： Training Computer vision Accuracy Computational modeling Stochastic processes Predictive models Reliability Faces

来源：评论

学校读者我要写书评

暂无评论

Competition on robust deep learning

引用

National Science Review 2023年第6期10卷 13-15页

作者： Yinpeng Dong Chang Liu Wenzhao Xiang Hang Su Jun Zhu Department of Computer Science and Technology Institute for AI Tsinghua-Bosch Joint ML Center THBI Lab BNRist Center Tsinghua University Institute of Image Communication and Networks Engineering in the Department of Electronic Engineering (EE) Shanghai Jiao Tong University Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Peng Cheng Laboratory Pazhou Laboratory (Huangpu)

PROBLEM In recent years,the rapid development of artificial intelligence (AI) technology,especially machine learning and deep learning, is profoundly changing human production and *** various fields,such as robotics,face recognition,autonomous driving and healthcare,AI is playing an important ***,although AI is promoting the technological revolution and industrial progress,its security risks are often *** studies have found that the wellperforming deep learning models are extremely vulnerable to adversarial examples [1-3].The adversarial examples are crafted by applying small,humanimperceptible perturbations to natural examples,but can mislead deep learning models to make wrong *** vulnerability of deep learning models to adversarial examples can raise security and safety threats to various realworld applications.

关键词： robustness adversarial example adversarial training deep learning

来源：评论

学校读者我要写书评

暂无评论

High Contrast Ratio 4-to-2 Plasmonic Encoder Utilizing Cascaded Ring Resonators

High Contrast Ratio 4-to-2 Plasmonic Encoder Utilizing Casca...

引用

International Conference on Electronic Engineering and Informatics (EEI)

作者： Yan Chen Yiyuan Xie Junxiong Chai Yichen Ye College of Electronic and Information Engineering Southwest University Chongqing China Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing Chongqing China Key Laboratory of Networks and Cloud Computing Security of Universities in Chongqing Chongqing China

ISBN: (数字)9798350353594

ISBN: (纸本)9798350353600

In this paper, a novel plasmonic 4-to-2 encoder comprising cascaded ring resonators coated with graphene layers and two metal-insulator-metal (MIM) waveguides. The encoding function operates at 850 nm by modulating the intensity of pump beam focused on the graphene layer to manipulate the state of the plasmonic resonators. The performance of the encoder is analyzed utilizing the finite-difference time-domain method, demonstrating a high contrast ratio of 15.1 dB. Thus, this efficient 4-to-2 optical encoder is well-suited for integration into optical integrated computing devices.

关键词： Integrated optics Optical switches Graphene Plasmons Optical pumping Encoding Optical modulation Optical ring resonators Optical devices Finite difference methods

来源：评论

学校读者我要写书评

暂无评论

A U-shape Compensation Structure for Differential-to-Common Mode Conversion Noise Suppression in 90°-Bended differential Line 13

A U-shape Compensation Structure for Differential-to-Common ...

引用

13th Asia-Pacific International Symposium on Electromagnetic Compatibility and Technical Exhibition, APEMC 2022

作者： He, Zhikang Zhu, Haoran Anhui Province Anhui University Information Materials and Intelligent Sensing Laboratory Hefei230039 China Anhui University Ministry of Education Key Lab of Intelligent Computing and Signal Processing Hefei230039 China

ISBN: (数字)9781665416719

ISBN: (纸本)9781665416719

a U-shaped structure, based on the equivalent lumped circuit of differential transmission line, is proposed to suppress the noise of differential-common-mode conversion. With the equivalent lumped circuit, the cause of mode conversion noise is analyzed. The U-shaped structure has reached the suppression level of 24.31 dB from DC to 10 GHz according to the simulated result. © 2022 IEEE.

关键词： Electric lines

来源：评论

学校读者我要写书评

暂无评论

Predicting Calibrated Conversion Rate of Online Advertising Using a Multi-task Mixture-of-Experts Calibration Model 12th

Predicting Calibrated Conversion Rate of Online Advertising...

引用

12th CCF Conference on BigData, BigData 2024

作者： Zhang, Xinyue Guo, Yuyao Ao, Xiang School of Information Engineering China University of Geosciences Beijing China Beijing China Key Lab of Intelligent Information Processing Institute of Computing Technology CAS Beijing China

ISBN: (纸本)9789819610235

Accurately predicting conversion rate (CVR) is paramount in online advertising. However, traditional models may face problems such as delayed feedback, where there is a delay of an indeterminate amount of time between click and conversion. Calibration is an effective way to optimize conversion rate estimates in online advertising. Unlike conversion delays, post-click user behaviors occur rapidly and are informative to conversion rate prediction. Our proposed solution, the Multi-Task Mixture-of-Experts Calibration (MTMEC) framework, integrates multi-task learning and mixture-of-experts models. It modifies CVR prediction using post-click user behavior data, utilizing streaming learning for real-time data access. Each task is weighted by a gating network, enabling adaptive loss functions through multi-task learning. Parametric scaling further minimizes calibration errors, enhancing prediction accuracy without excessive parameters. Experiments on real-world datasets validate the effectiveness of MTMEC. It improves model prediction and reduces calibration errors. This framework offers a robust solution for online advertising, bridging the gap between calibration accuracy and system responsiveness. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

A Miniaturized Microwave Limiter by Using T-Type LC Network Topology with GaAs Technology 13

A Miniaturized Microwave Limiter by Using T-Type LC Network ...

引用

13th Asia-Pacific International Symposium on Electromagnetic Compatibility and Technical Exhibition, APEMC 2022

作者： Wang, Jun Zhu, Haoran Anhui University Information Materials and Intelligent Sensing Laboratory of Anhui Province Hefei230039 China Anhui University Ministry of Education Key Lab of Intelligent Computing & Signal Processing Hefei230039 China

ISBN: (数字)9781665416719

ISBN: (纸本)9781665416719

A miniaturized ultra-wideband microwave limiter with low insertion loss is presented in this paper. This limiter adopts a three-stage antiparallel diode structure. A T-type LC network topology consisting of two spiral inductors and a parallel grounded metal-insulator-metal (MIM) capacitor is utilized to replace the traditional λ/4 transmission line in series between the limiting circuits. Compared with the traditional topology, the proposed limiter has the advantages of miniaturization and ultra-wideband. The area of the presented microwave limiter chip is only 1.25×0.75mm2. The simulation results show that the limiter can work in 0.05-18GHz. Insertion loss is less than 0.65dB at 18GHz. The output power can be maintained below 15dBm with a maximum power input of 40dBm continuous wave. © 2022 IEEE.

关键词： Network topology

来源：评论

学校读者我要写书评

暂无评论

Object-to-Manipulation Graph for Affordance Navigation

引用

CAAI Artificial Intelligence Research 2024年第1期3卷 178-186页

作者： Xinhang Song Bohan Wang Liye Dong Gongwei Chen Xinyun Hu Shuqiang Jiang Key Lab of Intelligent Information Processing of Chinese Academy of Sciences(CAS) Institute of Computing TechnologyCASBeijing 100190China University of Chinese Academy of Sciences Beijing 100049China

Object navigation,whose goal is to let the agent to reach some places(or objects),has been a popular topic in embodied Artificial Intelligence(AI)***,in our real-world applications,it is more practical to find the targets with particular goals,raising the new requirements of finding the places to achieve the particular *** this paper,we define a new task of affordance navigation,whose goal is to find possible places to accomplish the required functions,achieving some particular *** first introduce a new dataset for affordance navigation,collected by the proposed affordance *** order to avoid the high cost of labor,the groundtruth of each episode which is annotated with the interaction data provided by the AI2-THOR *** addition,we also propose an affordance navigation framework,where an Object-to-Manipulation Graph(OMG)is constructed and optimized to emphasize the corresponding nodes(including object nodes and manipulation nodes).Finally,a navigation policy is implemented(trained by reinforcement learning)to guide the navigation to the target *** results on AI2-THOR simulator illustrate the effectiveness of the proposed approach,which achieves significant gains of 14.0%and 11.7%(on success rate and Success weighted by Path Length(SPL),respectively)over the baseline model.

关键词： navigation affordance manipulation graph neural network

来源：评论

学校读者我要写书评

暂无评论

AUCSeg: AUC-oriented pixel-level long-tail semantic segmentation 24

AUCSeg: AUC-oriented pixel-level long-tail semantic segmenta...

引用

Proceedings of the 38th International Conference on Neural information processing Systems

作者： Boyu Han Qianqian Xu Zhiyong Yang Shilong Bao Peisong Wen Yangbangyan Jiang Qingming Huang Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and School of Computer Science and Tech. University of Chinese Academy of Sciences Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and Peng Cheng Laboratory School of Computer Science and Tech. University of Chinese Academy of Sciences School of Computer Science and Tech. University of Chinese Academy of Sciences and Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and Key Laboratory of Big Data Mining and Knowledge Management CAS

ISBN: (纸本)9798331314385

The Area Under the ROC Curve (AUC) is a well-known metric for evaluating instance-level long-tail learning problems. In the past two decades, many AUC optimization methods have been proposed to improve model performance under long-tail distributions. In this paper, we explore AUC optimization methods in the context of pixel-level long-tail semantic segmentation, a much more complicated scenario. This task introduces two major challenges for AUC optimization techniques. On one hand, AUC optimization in a pixel-level task involves complex coupling across loss terms, with structured inner-image and pairwise inter-image dependencies, complicating theoretical analysis. On the other hand, we find that mini-batch estimation of AUC loss in this case requires a larger batch size, resulting in an unaffordable space complexity. To address these issues, we develop a pixel-level AUC loss function and conduct a dependency-graph-based theoretical analysis of the algorithm's generalization ability. Additionally, we design a Tail-Classes Memory Bank (T-Memory Bank) to manage the significant memory demand. Finally, comprehensive experiments across various benchmarks confirm the effectiveness of our proposed AUCSeg method. The code is available at https://***/boyuh/AUCSeg.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Speculative decoding with CTC-based draft model for LLM inference acceleration 24

Speculative decoding with CTC-based draft model for LLM infe...

引用

Proceedings of the 38th International Conference on Neural information processing Systems

作者： Zhuofan Wen Shangtong Gui Yang Feng Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences and University of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences and State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences and University of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences and Key Laboratory of Al Safety Chinese Academy of Sciences and University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798331314385

Inference acceleration of large language models (LLMs) has been put forward in many application scenarios and speculative decoding has shown its advantage in addressing inference acceleration. Speculative decoding usually introduces a draft model to assist the base LLM where the draft model produces drafts and the base LLM verifies the draft for acceptance or rejection. In this framework, the final inference speed is decided by the decoding speed of the draft model and the acceptance rate of the draft provided by the draft model. Currently the widely used draft models usually generate draft tokens for the next several positions in a non-autoregressive way without considering the correlations between draft tokens. Therefore, it has a high decoding speed but an unsatisfactory acceptance rate. In this paper, we focus on how to improve the performance of the draft model and aim to accelerate inference via a high acceptance rate. To this end, we propose a CTC-based draft model which strengthens the correlations between draft tokens during the draft phase, thereby generating higher-quality draft candidate sequences. Experiment results show that compared to strong baselines, the proposed method can achieve a higher acceptance rate and hence a faster inference speed.

关键词：

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：