检索结果-内蒙古大学图书馆

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Saehyung Lee Jisoo Mok Sangha Park Yongho Shin Dahuin Jung Sungroh Yoon Department of Electrical and Computer Engineering Seoul National University Qualcomm Korea YH Seoul South Korea School of Computer Science and Engineering Soongsil University Department of Electrical and Computer Engineering and Interdisciplinary Program in Artificial Intelligence Seoul National University

ISBN: (纸本)9798331314385

In our study, we explore methods for detecting unwanted content lurking in visual datasets. We provide a theoretical analysis demonstrating that a model capable of successfully partitioning visual data can be obtained using only textual data. Based on the analysis, we propose Hassle-Free Textual Training (HFTT), a streamlined method capable of acquiring detectors for unwanted visual content, using only synthetic textual data in conjunction with pre-trained vision-language models. HFTT features an innovative objective function that significantly reduces the necessity for human involvement in data annotation. Furthermore, HFTT employs a clever textual data synthesis method, effectively emulating the integration of unknown visual data distribution into the training process at no extra cost. The unique characteristics of HFTT extend its utility beyond traditional out-of-distribution detection, making it applicable to tasks that address more abstract concepts. We complement our analyses with experiments in out-of-distribution detection and hateful image detection. Our codes are available at https://***/Saehyung-Lee/HFTT

关键词：

来源：评论

学校读者我要写书评

暂无评论

ENTROPY IS NOT ENOUGH FOR TEST-TIME ADAPTATION: FROM THE PERSPECTIVE OF DISENTANGLED FACTORS 12

ENTROPY IS NOT ENOUGH FOR TEST-TIME ADAPTATION: FROM THE PER...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Lee, Jonghyun Jung, Dahuin Lee, Saehyung Park, Junsung Shin, Juhyeon Hwang, Uiwon Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Korea Republic of School of Computer Science and Engineering Soongsil University Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of Division of Digital Healthcare Yonsei University Korea Republic of AIIS ASRI INMC ISRC Seoul National University Korea Republic of

Test-time adaptation (TTA) fine-tunes pre-trained deep neural networks for unseen test data. The primary challenge of TTA is limited access to the entire test dataset during online updates, causing error accumulation. To mitigate it, TTA methods have utilized the model output's entropy as a confidence metric that aims to determine which samples have a lower likelihood of causing error. Through experimental studies, however, we observed the unreliability of entropy as a confidence metric for TTA under biased scenarios and theoretically revealed that it stems from the neglect of the influence of latent disentangled factors of data on predictions. Building upon these findings, we introduce a novel TTA method named Destroy Your Object (DeYO), which leverages a newly proposed confidence metric named Pseudo-Label Probability Difference (PLPD). PLPD quantifies the influence of the shape of an object on prediction by measuring the difference between predictions before and after applying an object-destructive transformation. DeYO consists of sample selection and sample weighting, which employ entropy and PLPD concurrently. For robust adaptation, DeYO prioritizes samples that dominantly incorporate shape information when making predictions. Our extensive experiments demonstrate the consistent superiority of DeYO over baseline methods across various scenarios, including biased and wild. Project page is publicly available at https://***/DeYO/. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

CLeAR: continual learning on algorithmic reasoning for human-like intelligence 23

CLeAR: continual learning on algorithmic reasoning for human...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Bong Gyun Kang HyunGi Kim Dahuin Jung Sungroh Yoon Interdisciplinary Program in Artificial Intelligence Seoul National University Department of Electrical and Computer Engineering Seoul National University Interdisciplinary Program in Artificial Intelligence Seoul National University and Department of Electrical and Computer Engineering Seoul National University

Continual learning (CL) aims to incrementally learn multiple tasks that are presented sequentially. The significance of CL lies not only in the practical importance but also in studying the learning mechanisms of humans who are excellent continual learners. While most research on CL has been done on structured data such as images, there is a lack of research on CL for abstract logical concepts such as counting, sorting, and arithmetic, which humans learn gradually over time in the real world. In this work, for the first time, we introduce novel algorithmic reasoning (AR) methodology for continual tasks of abstract concepts: CLeAR. Our methodology proposes a one-to-many mapping of input distribution to a shared mapping space, which allows the alignment of various tasks of different dimensions and shared semantics. Our tasks of abstract logical concepts, in the form of formal language, can be classified into Chomsky hierarchies based on their difficulty. In this study, we conducted extensive experiments consisting of 15 tasks with various levels of Chomsky hierarchy, ranging from in-hierarchy to inter-hierarchy scenarios. CLeAR not only achieved near zero forgetting but also improved accuracy during following tasks, a phenomenon known as backward transfer, while previous CL methods designed for image classification drastically failed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On the Impact of Knowledge Distillation for Model Interpretability 40

On the Impact of Knowledge Distillation for Model Interpreta...

引用

40th International Conference on Machine Learning, ICML 2023

作者： Han, Hyeongrok Siwon, Kim Choi, Hyun-Soo Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Seoul Korea Republic of Department of Computer Science and Engineering Seoul National University of Science and Technology Seoul Korea Republic of ZIOVISION Inc. Chuncheon Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul Korea Republic of

Several recent studies have elucidated why knowledge distillation (KD) improves model performance. However, few have researched the other advantages of KD in addition to its improving model performance. In this study, we have attempted to show that KD enhances the interpretability as well as the accuracy of models. We measured the number of concept detectors identified in network dissection for a quantitative comparison of model interpretability. We attributed the improvement in interpretability to the class-similarity information transferred from the teacher to student models. First, we confirmed the transfer of class-similarity information from the teacher to student model via logit distillation. Then, we analyzed how class-similarity information affects model interpretability in terms of its presence or absence and degree of similarity information. We conducted various quantitative and qualitative experiments and examined the results on different datasets, different KD methods, and according to different measures of interpretability. Our research showed that KD models by large models could be used more reliably in various fields. The code is available at https://***/Rok07/KD_***. © 2023 Proceedings of Machine Learning Research. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Variance-stationary Differentiable NAS 32

Variance-stationary Differentiable NAS

引用

32nd British Machine Vision Conference, BMVC 2021

作者： Choe, Hyeokjun Na, Byunggook Mok, Jisoo Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Seoul Korea Republic of Interdisciplinary Program in AI Seoul National University Seoul Korea Republic of

Differentiable architecture search (DARTS) has become the popular method of neural architecture search (NAS) due to its adaptability and low computational cost. However, following the publication of DARTS, it has been found that DARTS often yields a suboptimal neural architecture because architecture parameters do not accurately represent operation strengths. Through extensive theoretical analysis and empirical observations, we reveal that this issue occurs as a result of the existence of unnormalized operations. Based on our finding, we propose a novel variance-stationary differentiable architecture search (VS-DARTS), which consists of node normalization, local adaptive learning rate, and pβ-continuous relaxation. Comprehensively, VS-DARTS makes the architecture parameters a more reliable metric for deriving a desirable architecture without increasing the search cost. In addition to the theoretical motivation behind all components of VS-DARTS, we provide strong experimental results to demonstrate that they synergize to significantly improve the search performance. The architecture searched by VS-DARTS achieves the test error of 2.50% on CIFAR-10 and 24.7% on ImageNet. © 2021. The copyright of this document resides with its authors.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

STEIN LATENT OPTIMIZATION FOR GENERATIVE ADVERSARIAL NETWORKS 10

STEIN LATENT OPTIMIZATION FOR GENERATIVE ADVERSARIAL NETWORK...

引用

10th International Conference on Learning Representations, ICLR 2022

作者： Hwang, Uiwon Kim, Heeseung Jung, Dahuin Jang, Hyemi Lee, Hyungyu Yoon, Sungroh Department of Electrical and Computer Engineering AIIS ASRI INMC ISRC NSI and Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul08826 Korea Republic of

Generative adversarial networks (GANs) with clustered latent spaces can perform conditional generation in a completely unsupervised manner. In the real world, the salient attributes of unlabeled data can be imbalanced. However, most of existing unsupervised conditional GANs cannot cluster attributes of these data in their latent spaces properly because they assume uniform distributions of the attributes. To address this problem, we theoretically derive Stein latent optimization that provides reparameterizable gradient estimations of the latent distribution parameters assuming a Gaussian mixture prior in a continuous latent space. Structurally, we introduce an encoder network and novel unsupervised conditional contrastive loss to ensure that data generated from a single mixture component represent a single attribute. We confirm that the proposed method, named Stein Latent Optimization for GANs (SLOGAN), successfully learns balanced or imbalanced attributes and achieves state-of-the-art unsupervised conditional generation performance even in the absence of attribute information (e.g., the imbalance ratio). Moreover, we demonstrate that the attributes to be learned can be manipulated using a small amount of probe data. © 2022 ICLR 2022 - 10th International Conference on Learning Representationss. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

On the powerfulness of textual outlier exposure for visual OoD detection 23

On the powerfulness of textual outlier exposure for visual O...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Sangha Park Jisoo Mok Dahuin Jung Saehyung Lee Sungroh Yoon Department of Electrical and Computer Engineering Seoul National University Department of Electrical and Computer Engineering Seoul National University and Interdisciplinary Program in Artificial Intelligence Seoul National University

Successful detection of Out-of-Distribution (OoD) data is becoming increasingly important to ensure safe deployment of neural networks. One of the main challenges in OoD detection is that neural networks output overconfident predictions on OoD data, make it difficult to determine OoD-ness of data solely based on their predictions. Outlier exposure addresses this issue by introducing an additional loss that encourages low-confidence predictions on OoD data during training. While outlier exposure has shown promising potential in improving OoD detection performance, all previous studies on outlier exposure have been limited to utilizing visual outliers. Drawing inspiration from the recent advancements in vision-language pre-training, this paper venture out to the uncharted territory of textual outlier exposure. First, we uncover the benefits of using textual outliers by replacing real or virtual outliers in the image-domain with textual equivalents. Then, we propose various ways of generating preferable textual outliers. Our extensive experiments demonstrate that generated textual outliers achieve competitive performance on large-scale OoD and hard OoD benchmarks. Furthermore, we conduct empirical analyses of textual outliers to provide primary criteria for designing advantageous textual outliers: near-distribution, descriptiveness, and inclusion of visual semantics. Code is available at https://***/wiarae/TOE

关键词：

来源：评论

学校读者我要写书评

暂无评论

Semantic Token Reweighting for Interpretable and Controllable Text Embeddings in CLIP

arXiv

引用

arXiv 2024年

作者： Kim, Eunji Shim, Kyuhong Chang, Simyung Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Korea Republic of Qualcomm AI Research Qualcomm Korea YH Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of

A text encoder within Vision-Language Models (VLMs) like CLIP plays a crucial role in translating textual input into an embedding space shared with images, thereby facilitating the interpretative analysis of vision tasks through natural language. Despite the varying significance of different textual elements within a sentence depending on the context, efforts to account for variation of importance in constructing text embeddings have been lacking. We propose a framework of Semantic Token Reweighting to build Interpretable text embeddings (SToRI), which incorporates controllability as well. SToRI refines the text encoding process in CLIP by differentially weighting semantic elements based on contextual importance, enabling finer control over emphasis responsive to data-driven insights and user preferences. The efficacy of SToRI is demonstrated through comprehensive experiments on few-shot image classification and image retrieval tailored to user preferences. © 2024, CC BY-NC-SA.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

VRGrip: Developing a Grip Strength Training Platform Integrating a Wireless E-Textile Forearm Band with an Adaptive 3D VR Game Environment

VRGrip: Developing a Grip Strength Training Platform Integra...

引用

2023 IEEE MIT Undergraduate Research Technology Conference, URTC 2023

作者： Chatragadda, Lohith Fletcher, aiden Delmonico, Matthew J. Mankodiya, Kunal Solanki, Dhaval University of Rhode Island Interdisciplinary Neuroscience Program KingstonRI United States University of Rhode Island Department of Kinesiology KingstonRI United States University of Rhode Island Department of Electrical Computer and Biomedical Engineering KingstonRI United States

ISBN: (纸本)9798350308600

Neurodegenerative disease is a growing global problem. Many of these diseases such as Parkinson's disease can cause grip strength weakness. In this work, we focused on developing an e-Textile based EMG acquisition system interfaced with an adaptive VR game engine for detecting hand squeeze actions. We prototyped and performed preliminary tests on a grip detection system consisting of: 1) an e-Textile forearm band (E-band), 2) a portable data acquisition module (DAM), and 3) an adaptive 3D VR game engine. Digital health solutions such as our VRGrip system widen the scope of in-home rehabilitation and assessment, and we aimed to make the first step in creating a system for grip strength rehabilitation. To validate our concept, we performed preliminary tests. These tests revealed that the Bluetooth communication protocol between DAM and the game engine was reliable, that the adaptive game engine successfully tailors the game's difficulty level to the user's performance, and that the system was reliable at detecting hand squeezes (F=0.96). © 2023 IEEE.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Learn2Evade: Learning-based generative model for evading PDF malware classifiers

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2021年第4期2卷 299-313页

作者： Bae, Ho Lee, Younghan Kim, Yohan Hwang, Uiwon Yoon, Sungroh Paek, Yunheung Department of Cyber Security EwhaWomans University Seoul03760 Korea Republic of Department of Electrical and Computer Engineering Seoul National University Seoul08826 Korea Republic of Department of Electrical and Computer Engineering Interdisciplinary Program in Bioinformatics Interdisciplinary Program in Artificial Intelligence Automation and Systems Research Institute Institute of NewMedia and Communications Institute of Engineering Research Seoul National University Seoul08826 Korea Republic of

Recent research has shown that a small perturbation to an input may forcibly change the prediction of a machine learning (ML) model. Such variants are commonly referred to as adversarial examples. Early studies have focused mostly on ML models for image processing and expanded to other applications, including those for malware classification. In this article, we focus on the problem of finding adversarial examples against ML-based portable document format (PDF) malware *** deem that our problem is more challenging than those againstMLmodels for image processing because of the highly complex data structure of PDF and of an additional constraint that the generated PDF should exhibit malicious behavior. To resolve our problem, we propose a variant of generative adversarial networks that generate evasive variant PDF malware (without any crash), which can be classified as benign by various existing classifiers yetmaintaining the original malicious behavior. Our model exploits the target classifier as the second discriminator to rapidly generate an evasive variant PDF with our new feature selection process that includes unique features extracted from malicious PDF files. We evaluate our technique against three representative PDF malware classifiers (Hidost 13, Hidost 16, and PDFrate-v2) and further examine its effectiveness with AntiVirus engines from VirusTotal. To the best of our knowledge, our work is the first to analyze the performance against the commercial AntiVirus engines. Our model finds, with great speed, evasive variants for all selected seeds against state-of-The-Art PDF malware classifiers and raises a serious security concern in the presence of adversaries. © 2021 Institute of electrical and Electronics Engineers Inc.. All rights reserved.

关键词： Generative adversarial networks

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：