检索结果-内蒙古大学图书馆

Reducing information bottleneck for weakly supervised semantic segmentation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Lee, Jungbeom Choi, Jooyoung Mok, Jisoo Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University ASRI INMC ISRC Institute of Engineering Research Seoul National University

Weakly supervised semantic segmentation produces pixel-level localization from class labels;however, a classifier trained on such labels is likely to focus on a small discriminative region of the target object. We interpret this phenomenon using the information bottleneck principle: the final layer of a deep neural network, activated by the sigmoid or softmax activation functions, causes an information bottleneck, and as a result, only a subset of the task-relevant information is passed on to the output. We first support this argument through a simulated toy experiment and then propose a method to reduce the information bottleneck by removing the last activation function. In addition, we introduce a new pooling method that further encourages the transmission of information from non-discriminative regions to the classification. Our experimental evaluations demonstrate that this simple modification significantly improves the quality of localization maps on both the PASCAL VOC 2012 and MS COCO 2014 datasets, exhibiting a new state-of-the-art performance for weakly supervised semantic segmentation. The code is available at: https://***/jbeomlee93/RIB. © 2021, CC BY-NC-SA.

关键词： Deep neural networks

Comparison of encrypted control approaches and tutorial on dynamic systems using LWE-based homomorphic encryption

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Kim, Junsoo Kim, Dongwoo Song, Yongsoo Shim, Hyungbo Sandberg, Henrik Johansson, Karl H. Department of Electrical and Information Engineering Seoul National University of Science and Technology Seoul Korea Republic of Western Digital Research MilpitasCA United States Department of Computer Science and Engineering Seoul National University Seoul Korea Republic of ASRI Department of Electrical and Computer Engineering Seoul National University Seoul Korea Republic of School of Electrical Engineering and Computer Science and Digital Futures KTH Royal Institute of Technology Stockholm Sweden

Encrypted control has been introduced to protect controller data by encryption at the stage of computation and communication, by performing the computation directly on encrypted data. In this article, we first review and categorize recent relevant studies on encrypted control. Approaches based on homomorphic encryption, multi-party computation, and secret sharing are introduced, compared, and then discussed with respect to computational complexity, communication load, enabled operations, security, and research directions. We proceed to discuss a current challenge in the application of homomorphic encryption to dynamic systems, where arithmetic operations other than integer addition and multiplication are limited. We also introduce a homomorphic cryptosystem called "GSW-LWE" and discuss its benefits that allow for recursive multiplication of encrypted dynamic systems, without use of computationally expensive bootstrapping techniques. © 2022, CC BY.

关键词： Cryptography

Continuous-time optimization algorithm using integral control

学校读者我要写书评

暂无评论

Journal of Institute of Control, Robotics and Systems 2019年第9期25卷 853-857页

作者： Lee, Seungjoon ASRI Department of Electrical and Computer Engineering Seoul National University Korea Republic of

In this paper, a new continuous-time optimization algorithm motivated by integral control is proposed. It is shown that the solution of the proposed algorithm converges to the optimal solution and converges exponentially if the objective function is strongly convex. Convergence rate of the proposed algorithm is also analyzed for f(x)=|x| and its performance is compared with other algorithms. In particular, it is shown that the vanilla gradient descent method and gradient descent with momentum converge linearly in time, while the proposed algorithm is shown to decrease quadratically and has similar behavior to Nesterov’s gradient method. In addition, a gradient restarting scheme is proposed to reduce oscillatory behavior and to improve performance. © ICROS 2019.

关键词： Convex optimization

Mutual suppression network for video prediction using disentangled features 30

学校读者我要写书评

暂无评论

Mutual suppression network for video prediction using disent...

30th British Machine Vision Conference, BMVC 2019

作者： Lee, Jungbeom Lee, Jangho Lee, Sungmin Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Korea Republic of ASRI INMC ISRC Institute of Engineering Research Seoul National University Korea Republic of

Video prediction has been considered a difficult problem because the video contains not only high-dimensional spatial information but also complex temporal information. Video prediction can be performed by finding features in recent frames, and using them to generate approximations to upcoming frames. We approach this problem by disentangling spatial and temporal features in videos. We introduce a mutual suppression network (MSnet) which are trained in an adversarial manner and then produces spatial features which are free of motion information, and motion features with no spatial information. MSnet then uses motion-guided connection within an encoder-decoder-based architecture to transform spatial features from a previous frame to the time of an upcoming frame. We show how MSnet can be used for video prediction using disentangled representations. We also carry out experiments to assess the effectiveness of our method to disentangle features. MSnet obtains better results than other recent video prediction methods even though it has simpler encoders. © 2019. The copyright of this document resides with its authors.

关键词： Signal encoding

Removing undesirable feature contributions using out-of-distribution data

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Lee, Saehyung Park, Changhwa Lee, Hyungyu Yi, Jihun Lee, Jonghyun Yoon, Sungroh Electrical and Computer Engineering AIIS ASRI INMC Institute of Engineering Research Seoul National University Seoul08826 Korea Republic of

Several data augmentation methods deploy unlabeled-in-distribution (UID) data to bridge the gap between the training and inference of neural networks. However, these methods have clear limitations in terms of availability of UID data and dependence of algorithms on pseudo-labels. Herein, we propose a data augmentation method to improve generalization in both adversarial and standard learning by using out-of-distribution (OOD) data that are devoid of the abovementioned issues. We show how to improve generalization theoretically using OOD data in each learning scenario and complement our theoretical analysis with experiments on CIFAR-10, CIFAR-100, and a subset of ImageNet. The results indicate that undesirable features are shared even among image data that seem to have little correlation from a human point of view. We also present the advantages of the proposed method through comparison with other data augmentation methods, which can be used in the absence of UID data. Furthermore, we demonstrate that the proposed method can further improve the existing state-of-the-art adversarial training. Copyright © 2021, The Authors. All rights reserved.

关键词： Image enhancement

Documentation on Encrypted Dynamic Control Simulation Code using Ring-LWE based Cryptosystems

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Jang, Yeongjun Lee, Joowon Kim, Junsoo ASRI Department of Electrical and Computer Engineering Seoul National University Korea Republic of Department of Electrical and Information Engineering Seoul National University of Science and Technology Korea Republic of

Encrypted controllers offer secure computation by employing modern cryptosystems to execute control operations directly over encrypted data without decryption. However, incorporating cryptosystems into dynamic controllers significantly increases the computational load. This paper aims to provide an accessible guideline for running encrypted controllers using an open-source library Lattigo, which supports an efficient implementation of Ring-Learing With Errors (LWE) based encrypted controllers, and our explanations are assisted with example codes that are fully available at https://***/CDSL-EncryptedControl/CDSL. © 2025, CC BY.

关键词： Networked control systems

Anti-Adversarially Manipulated Attributions for Weakly Supervised Semantic Segmentation and Object Localization

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Lee, Jungbeom Kim, Eunji Mok, Jisoo Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Seoul08826 Korea Republic of Interdisciplinary Program in AI AIIS ASRI INMC and ISRC Seoul National University Seoul08826 Korea Republic of

Obtaining accurate pixel-level localization from class labels is a crucial process in weakly supervised semantic segmentation and object localization. Attribution maps from a trained classifier are widely used to provide pixel-level localization, but their focus tends to be restricted to a small discriminative region of the target object. An AdvCAM is an attribution map of an image that is manipulated to increase the classification score produced by a classifier before the final softmax or sigmoid layer. This manipulation is realized in an anti-adversarial manner, so that the original image is perturbed along pixel gradients in directions opposite to those used in an adversarial attack. This process enhances non-discriminative yet class-relevant features, which make an insufficient contribution to previous attribution maps, so that the resulting AdvCAM identifies more regions of the target object. In addition, we introduce a new regularization procedure that inhibits the incorrect attribution of regions unrelated to the target object and the excessive concentration of attributions on a small region of the target object. Our method achieves a new state-of-the-art performance in weakly and semi-supervised semantic segmentation, on both the PASCAL VOC 2012 and MS COCO 2014 datasets. In weakly supervised object localization, it achieves a new state-of-the-art performance on the CUB-200-2011 and ImageNet-1K datasets. © 2022, CC BY-NC-ND.

关键词： Semantic Segmentation

Fully Decentralized Design of Initialization-free Distributed Network Size Estimation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Lee, Donggil Kim, Taekyoo Lee, Seungjoon Shim, Hyungbo Center for Intelligent and Interactive Robotics Korea Institute of Science and Technology Seoul02792 Korea Republic of The Train Control and Communication Team Korea Railroad Research Institute Uiwang16105 Korea Republic of NAVER Labs Seongnam13161 Korea Republic of ASRI Department of Electrical and Computer Engineering Seoul National University Seoul08826 Korea Republic of

In this paper, we propose a distributed scheme for estimating the network size, which refers to the total number of agents in a network. By leveraging a synchronization technique for multi-agent systems, we devise an agent dynamics that ensures convergence to an equilibrium point located near the network size regardless of its initial condition. Our approach is based on an assumption that each agent has a unique identifier, and an estimation algorithm for obtaining the largest identifier value. By adopting this approach, we successfully implement the agent dynamics in a fully decentralized manner, ensuring accurate network size estimation even when some agents join or leave the network. © 2024, CC BY-NC-ND.

关键词： Multi agent systems

Weakly Supervised Semantic Segmentation using Out-of-Distribution Data

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Lee, Jungbeom Oh, Seong Joon Yun, Sangdoo Choe, Junsuk Kim, Eunji Yoon, Sungroh Department Of Electrical And Computer Engineering Seoul National University Korea Republic of NAVER AI Lab University Of Tübingen Germany Department Of Computer Science And Engineering Sogang University Korea Republic of Interdisciplinary Program In AI AIIS ASRI INMC ISRC And NSI Seoul National University Korea Republic of

Weakly supervised semantic segmentation (WSSS) methods are often built on pixel-level localization maps obtained from a classifier. However, training on class labels only, classifiers suffer from the spurious correlation between foreground and background cues (e.g. train and rail), fundamentally bounding the performance of WSSS. There have been previous endeavors to address this issue with additional supervision. We propose a novel source of information to distinguish foreground from the background: Out-of-Distribution (OoD) data, or images devoid of foreground object classes. In particular, we utilize the hard OoDs that the classifier is likely to make false-positive predictions. These samples typically carry key visual features on the background (e.g. rail) that the classifiers often confuse as foreground (e.g. train), so these cues let classifiers correctly suppress spurious background cues. Acquiring such hard OoDs does not require an extensive amount of annotation efforts;it only incurs a few additional image-level labeling costs on top of the original efforts to collect class labels. We propose a method, W-OoD, for utilizing the hard OoDs. W-OoD achieves state-of-the-art performance on Pascal VOC 2012. The code is available at: https://***/naver-ai/w-ood. © 2022, CC BY-NC-SA.

关键词： Semantic Segmentation