检索结果-内蒙古大学图书馆

Proceedings of the 36th International Conference on Neural information processing Systems

作者： Shilong Bao Qianqian Xu Zhiyong Yang Yuan He Xiaochun Cao Qingming Huang State Key Laboratory of Information Security Institute of Information Engineering CAS and School of Cyber Security University of Chinese Academy of Sciences Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS School of Computer Science and Tech. University of Chinese Academy of Sciences Alibaba Group School of Cyber Science and Technology Shenzhen Campus Sun Yat-sen University Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and School of Computer Science and Tech. University of Chinese Academy of Sciences and Key Laboratory of Big Data Mining and Knowledge Management CAS and Peng Cheng Laboratory

ISBN: (纸本)9781713871088

Collab.rative Metric Learning (CML) has recently emerged as a popular method in recommendation systems (RS), closing the gap between metric learning and Collab.rative Filtering. Following the convention of RS, existing methods exploit unique user representation in their model design. This paper focuses on a challenging scenario where a user has multiple categories of interests. Under this setting, we argue that the unique user representation might induce preference bias, especially when the item category distribution is imbalanced. To address this issue, we propose a novel method called Diversity-Promoting Collab.rative Metric Learning (DPCML), with the hope of considering the commonly ignored minority interest of the user. The key idea behind DPCML is to include a multiple set of representations for each user in the system. Based on this embedding paradigm, user preference toward an item is aggregated from different embeddings by taking the minimum item-user distance among the user embedding set. Furthermore, we observe that the diversity of the embeddings for the same user also plays an essential role in the model. To this end, we propose a Diversity Control Regularization Scheme (DCRS) to accommodate the multi-vector representation strategy better. Theoretically, we show that DPCML could generalize well to unseen test data by tackling the challenge of the annoying operation that comes from the minimum value. Experiments over a range of benchmark datasets speak to the efficacy of DPCML.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LightXML: Transformer with dynamic negative sampling for high-performance extreme multi-lab.l text classification

arXiv

引用

arXiv 2021年

作者： Jiang, Ting Wang, Deqing Sun, Leilei Yang, Huayi Zhao, Zhengyang Zhuang, Fuzhen SKLSDE and BDBC Lab Beihang University Beijing China Key Lab of Intelligent Information Processing of CAS Institute of Computing Technology CAS Beijing China Beijing Advanced Innovation Center for Imaging Theory and Technology Academy for Multidisciplinary Studies Capital Normal University Beijing China

Extreme Multi-lab.l text Classification (XMC) is a task of finding the most relevant lab.ls from a large lab.l set. Nowadays deep learning-based methods have shown significant success in XMC. However, the existing methods (e.g., AttentionXML and X-Transformer etc) still suffer from 1) combining several models to train and predict for one dataset, and 2) sampling negative lab.ls statically during the process of training lab.l ranking model, which reduces both the efficiency and accuracy of the model. To address the above problems, we proposed LightXML, which adopts end-to-end training and dynamic negative lab.ls sampling. In LightXML, we use generative cooperative networks to recall and rank lab.ls, in which lab.l recalling part generates negative and positive lab.ls, and lab.l ranking part distinguishes positive lab.ls from these lab.ls. Through these networks, negative lab.ls are sampled dynamically during lab.l ranking part training by feeding with the same text representation. Extensive experiments show that LightXML outperforms state-of-the-art methods in five extreme multi-lab.l datasets with much smaller model size and lower computational complexity. In particular, on the Amazon dataset with 670K lab.ls, LightXML can reduce the model size up to 72% compared to AttentionXML. Our code is availab.e at http://***/kongds/LightXML. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

DRAUC: an instance-wise distributionally robust AUC optimization framework 23

DRAUC: an instance-wise distributionally robust AUC optimiza...

引用

Proceedings of the 37th International Conference on Neural information processing Systems

作者： Siran Dai Qianqian Xu Zhiyong Yang Xiaochun Cao Qingming Huang SKLOIS Institute of Information Engineering CAS and School of Cyber Security University of Chinese Academy of Sciences Key Lab. of Intelligent Information Processing Institute of Computing Tech. CAS School of Computer Science and Tech. University of Chinese Academy of Sciences School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University School of Computer Science and Tech. University of Chinese Academy of Sciences and Key Lab. of Intelligent Information Processing Institute of Computing Tech. CAS and BDKM University of Chinese Academy of Sciences

The Area Under the ROC Curve (AUC) is a widely employed metric in long-tailed classification scenarios. Nevertheless, most existing methods primarily assume that training and testing examples are drawn i.i.d. from the same distribution, which is often unachievable in practice. Distributionally Robust Optimization (DRO) enhances model performance by optimizing it for the local worst-case scenario, but directly integrating AUC optimization with DRO results in an intractable optimization problem. To tackle this challenge, methodically we propose an instance-wise surrogate loss of Distributionally Robust AUC (DRAUC) and build our optimization framework on top of it. Moreover, we highlight that conventional DRAUC may induce lab.l bias, hence introducing distribution-aware DRAUC as a more suitable metric for robust AUC learning. Theoretically, we affirm that the generalization gap between the training loss and testing error diminishes if the training set is sufficiently large. Empirically, experiments on corrupted benchmark datasets demonstrate the effectiveness of our proposed method. Code is availab.e at: https://***/EldercatSAM/DRAUC.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A unified generalization analysis of re-weighting and logit-adjustment for imbalanced learning 23

A unified generalization analysis of re-weighting and logit-...

引用

Proceedings of the 37th International Conference on Neural information processing Systems

作者： Zitai Wang Qianqian Xu Zhiyong Yang Yuan He Xiaochun Cao Qingming Huang SKLOIS Institute of Information Engineering CAS and School of Cyber Security University of Chinese Academy of Sciences Key Lab. of Intelligent Information Processing Institute of Computing Tech. CAS School of Computer Science and Tech. University of Chinese Academy of Sciences Alibaba Group School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University School of Computer Science and Tech. University of Chinese Academy of Sciences and Key Lab. of Intelligent Information Processing Institute of Computing Tech. CAS and BDKM University of Chinese Academy of Sciences

Real-world datasets are typically imbalanced in the sense that only a few classes have numerous samples, while many classes are associated with only a few samples. As a result, a naïve ERM learning process will be biased towards the majority classes, making it difficult to generalize to the minority classes. To address this issue, one simple but effective approach is to modify the loss function to emphasize the learning on minority classes, such as re-weighting the losses or adjusting the logits via class-dependent terms. However, existing generalization analysis of such losses is still coarse-grained and fragmented, failing to explain some empirical results. To bridge this gap, we propose a novel technique named data-dependent contraction to capture how these modified losses handle different classes. On top of this technique, a fine-grained generalization bound is established for imbalanced learning, which helps reveal the mystery of re-weighting and logit-adjustment in a unified manner. Furthermore, a principled learning algorithm is developed based on the theoretical insights. Finally, the empirical results on benchmark datasets not only validate the theoretical results but also demonstrate the effectiveness of the proposed method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SSE-SAM: Balancing Head and Tail Classes Gradually through Stage-Wise SAM

arXiv

引用

arXiv 2024年

作者： Lyu, Xingyu Xu, Qianqian Yang, Zhiyong Lyu, Shaojie Huang, Qingming Key Lab. of Intelligent Information Processing Institute of Computing Tech. CAS China School of Computer Science and Tech University of Chinese Academy of Sciences China Tencent Corporate China BDKM University of Chinese Academy of Sciences China

Real-world datasets often exhibit a long-tailed distribution, where vast majority of classes known as tail classes have only few samples. Traditional methods tend to overfit on these tail classes. Recently, a new approach called Imbalanced SAM (ImbSAM) is proposed to leverage the generalization benefits of Sharpness-Aware Minimization (SAM) for long-tailed distributions. The main strategy is to merely enhance the smoothness of the loss function for tail classes. However, we argue that improving generalization in long-tail scenarios requires a careful balance between head and tail classes. We show that neither SAM nor ImbSAM alone can fully achieve this balance. For SAM, we prove that although it enhances the model’s generalization ability by escaping saddle point in the overall loss landscape, it does not effectively address this for tail-class losses. Conversely, while ImbSAM is more effective at avoiding saddle points in tail classes, the head classes are trained insufficiently, resulting in significant performance drops. Based on these insights, we propose Stage-wise Saddle Escaping SAM (SSE-SAM), which uses complementary strengths of ImbSAM and SAM in a phased approach. Initially, SSE-SAM follows the majority sample to avoid saddle points of the head-class loss. During the later phase, it focuses on tail-classes to help them escape saddle points. Our experiments confirm that SSE-SAM has better ability in escaping saddles both on head and tail classes, and shows performance improvements. Copyright © 2024, 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

Lifting the Answer: Reranking Candidates on Data Augmented Text-to-SQL

Lifting the Answer: Reranking Candidates on Data Augmented T...

引用

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Guang-Yu Cheng Shuo Yu Wen-Bin Jiang Shuai Ma Xiang Ao Qing He Henan Institutes of Advanced Technology Zhengzhou University Zhengzhou P.R. China Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China Baidu inc Beijing China

The text-to-SQL task is a realistic and challenging job, which aims to translate natural language questions into corresponding SQL queries. When attempting to generate SQL queries in the text-to-SQL task, prevailing semantic parsing models employ beam search to generate several candidates. Based on our pilot study, we observe that the gold-standard SQL answer may exist in the n-best candidate list produced by the decoder, rather than the first. Hence, we aim to lift the correct answer given several candidates generated by semantic parsing models for text-to-SQL. To this end, we propose a reranking module that reorders the n-best list of candidate SQL queries by pair-wise hinge loss. Meanwhile, a data augmentation module is leveraged to enrich the inadequate training instances for providing candidates with better qualities. These two modules can be easily grafted onto text-to-SQL backbone networks, and extensive experiments on the cross-domain text-to-SQL benchmark Spider demonstrate that our method achieves 73.8% in accuracy on the Spider dataset, surpassing the base model by up to 3.5%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Evolving boxes for fast vehicle detection

Evolving boxes for fast vehicle detection

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Li Wang Yao Lu Hong Wang Yingbin Zheng Hao Ye Xiangyang Xue Shanghai Key Lab of Intelligent Information Processing Fudan University Shanghai China Chinese Academy of Sciences Shanghai Advanced Research Institute Shanghai China School of Computer Science and Engineering University of Washington Seattle USA

ISBN: (纸本)9781509060689

We perform fast vehicle detection from traffic surveillance cameras. A novel deep learning framework, namely Evolving Boxes, is developed that proposes and refines the object boxes under different feature representations. Specifically, our framework is embedded with a light-weight proposal network to generate initial anchor boxes as well as to early discard unlikely regions; a fine-turning network produces detailed features for these candidate boxes. We show intriguingly that by applying different feature fusion techniques, the initial boxes can be refined for both localization and recognition. We evaluate our network on the recent DETRAC benchmark and obtain a significant improvement over the state-of-the-art Faster RCNN by 9.5% mAP. Further, our network achieves 9-13 FPS detection speed on a moderate commercial GPU.

关键词： Proposals Vehicle detection Machine learning Training Detectors Object detection Surveillance

来源：评论

学校读者我要写书评

暂无评论

A Fully 3D Printed Accelerometer for Movement Monitoring Applications 17

A Fully 3D Printed Accelerometer for Movement Monitoring App...

引用

17th IEEE International Conference on Nano/Micro Engineered and Molecular Systems, NEMS 2022

作者： Liu, Guandong Wang, Changhai Luo, Ruiqi Jia, Zhili Hou, Maojing Ma, Wei Intelligent Network Research Institute Zhejiang Lab Hangzhou311100 China Heriot-Watt University Institute of Sensors Signals and Systems School of Engineering & Physical Sciences EdinburghEH14 4AS United Kingdom Zhejiang University State Key Lab. of Mod. Optical Instrum. College of Information Science and Electronic Engineering Hangzhou310027 China National Institute of Metrology Center for Advanced Measurement Science Beijing100029 China

ISBN: (纸本)9781665483018

This paper presents a fully 3D printed accelerometer. With a multi-extruder 3D printer, the conductive PLA (polylactic acid) filament material was selectively printed on the normal PLA substrates to form the electrodes for the device. Therefore, both the conductive electrodes and the nonconductive mechanical structures of the capacitive accelerometer can be fully 3D printed within one hour without using any additional patterning process and metallization process. Compared with the traditional silicon- based fabrication methods, this approach is much faster and can fulfill the increasing demands of personalized customization. The fully 3D printed accelerometer had a sensitivity of 0.48 V/g, a nonlinearity error of 1.16% and exhibited good dynamic characteristics, which indicate the 3D printed device has a potential to be applied in movement monitoring in real time. The work demonstrates a fast and low-cost method for MEMS devices fabrication. © 2022 IEEE.

关键词： Accelerometers

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

arXiv

引用

arXiv 2024年

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

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 availab.e at https://***/boyuh/AUCSeg. © 2024, CC BY.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

intelligent Human Fall Detection for Home Surveillance

Intelligent Human Fall Detection for Home Surveillance

引用

Symposia and Workshops on Ubiquitous, Autonomic and Trusted computing, UIC-ATC

作者： Hong Lu Bohong Yang Rui Zhao Pengliang Qu Wenqiang Zhang Shanghai Key Lab. of Intelligent Information Processing Fudan University P. R. China Shanghai Engineering Research Center for Video Technology and System Fudan University P. R. China

ISBN: (纸本)9781479976478

We propose in this paper an intelligent system for human fall detection in indoor environments. It can serve as home surveillance for elderly person. Specifically, we detect the human body captured by camera using the Vibe algorithm. Then Gabor feature of a human body is extracted as observation feature. Based on the extracted feature, incidents are detected as the changes from the standing state to the fall state in the feature space. The feature is detected on single image and is effective and efficient. Compared with the motion features across images combined with biological inspired feed-forward network, our method can obtain more robust detection results.

关键词： Feature extraction Senior citizens Conferences Support vector machines Robustness Surveillance Visualization

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：