Filters








19,940 Hits in 5.7 sec

A Grid Service Framework for Metadata Management in Self-e-Learning Networks [chapter]

George Samaras, Kyriakos Karenos, Eleni Christodoulou
2004 Lecture Notes in Computer Science  
We use a Self e-Learning Network (Se-LeNe) as the testbed application and propose a set of services that are applicable in such a case in alignment to the Open Grid Services Architecture (OGSA).  ...  We concentrate on providing services for the utilization of Learning Objects' (LO) 1 metadata, the basic of which, however, are generic enough to be utilized by other Grid-based systems that need to make  ...  We use an educational e-learning application as a testbed and find that the usability of such a service set can be applied to multiple architectural models.  ... 
doi:10.1007/978-3-540-28642-4_30 fatcat:uzktuojfdvgrrcymwaiubgeujm

Self-Supervised Learning via Conditional Motion Propagation [article]

Xiaohang Zhan, Xingang Pan, Ziwei Liu, Dahua Lin, Chen Change Loy
2019 arXiv   pre-print
Extensive experiments demonstrate that our framework learns structural and coherent features; and achieves state-of-the-art self-supervision performance on several downstream tasks including semantic segmentation  ...  In this work, we design a new learning-from-motion paradigm to bridge these gaps.  ...  Context-based self-supervised learning methods typically distort or decompose the images and then learn to recover the missing information. For instance, Doersch et al.  ... 
arXiv:1903.11412v3 fatcat:b2lyv5witraqtdvbjeuzty2k7m

Self Semi Supervised Neural Architecture Search for Semantic Segmentation [article]

Loïc Pauletto and Massih-Reza Amini and Nicolas Winckler
2022 arXiv   pre-print
In this paper, we propose a Neural Architecture Search strategy based on self supervision and semi-supervised learning for the task of semantic segmentation.  ...  Our approach builds an optimized neural network (NN) model for this task by jointly solving a jigsaw pretext task discovered with self-supervised learning over unlabeled training data, and, exploiting  ...  In this work, we present a way to bridge between these three worlds. Our approach is based on self supervision and semi-supervised learning for semantic segmentation.  ... 
arXiv:2201.12646v2 fatcat:dqasniazhjhclm2kzjx6vwfimy

SPU-Net: Self-Supervised Point Cloud Upsampling by Coarse-to-Fine Reconstruction with Self-Projection Optimization [article]

Xinhai Liu, Xinchen Liu, Yu-Shen Liu, Zhizhong Han
2022 arXiv   pre-print
In the point feature expansion, we introduce a hierarchically learnable folding strategy to generate upsampled point sets with learnable 2D grids.  ...  Specifically, we propose a coarse-to-fine reconstruction framework, which contains two main components: point feature extraction and point feature expansion, respectively.  ...  Deep learning based point cloud upsampling methods.  ... 
arXiv:2012.04439v2 fatcat:p7ooplr2xfgrdmiwuzbpqwdhia

MarioNette: Self-Supervised Sprite Learning [article]

Dmitriy Smirnov, Michael Gharbi, Matthew Fisher, Vitor Guizilini, Alexei A. Efros, Justin Solomon
2021 arXiv   pre-print
We propose a deep learning approach that decomposes sprite-based video animations into a disentangled representation of recurring graphic elements in a self-supervised manner.  ...  By jointly learning a dictionary of possibly transparent patches and training a network that places them onto a canvas, we deconstruct sprite-based content into a sparse, consistent, and explicit representation  ...  Our contributions include the following: • We describe a grid-based anchor system along with a learned dictionary of textured patches (with transparency) to extract a sprite-based image representation.  ... 
arXiv:2104.14553v2 fatcat:v6romfuzbjfkdagcfb3f2q2s2i

Developing Initial State Fuzzy Cognitive Maps with Self-Organizing Maps

Marcel Wehrle, Edy Portmann, Alexander Denzler, Andreas Meier
2015 International Workshop on Artificial Intelligence and Cognition  
Through the use of self-organizing maps, fuzzy cognitive maps are constructed. The fuzzy cognitive map is a generated representation of the emergent web semantics of the dataset.  ...  Following a design science research approach, a prototype has been implemented as a proof of concept.  ...  The usual arrangement of nodes is a twodimensional regular spacing in a hexagonal or rectangular grid. To overcome the border effect, spherical grids have been introduced [24, 25] .  ... 
dblp:conf/aic/WehrlePDM15 fatcat:myn2ghzfkvd5vavbgp3vsuyel4

Graph Self-supervised Learning with Accurate Discrepancy Learning [article]

Dongki Kim, Jinheon Baek, Sung Ju Hwang
2022 arXiv   pre-print
To tackle such limitations, we propose a framework that aims to learn the exact discrepancy between the original and the perturbed graphs, coined as Discrepancy-based Self-supervised LeArning (D-SLA).  ...  Predictive learning and contrastive learning are the two most prevalent approaches for graph self-supervised learning. However, they have their own drawbacks.  ...  Method In this section, we introduce our novel graph self-supervised learning framework, Discrepancy-based Self-supervised LeArning (D-SLA), which is illustrated in Figure 2 .  ... 
arXiv:2202.02989v4 fatcat:haippvtpbvgtvf4yhr6555wh5a

Self-Path: Self-supervision for Classification of Pathology Images with Limited Annotations [article]

Navid Alemi Koohbanani, Balagopal Unnikrishnan, Syed Ali Khurram, Pavitra Krishnaswamy, Nasir Rajpoot
2020 arXiv   pre-print
The proposed approach, which we term as Self-Path, is a multi-task learning approach where the main task is tissue classification and pretext tasks are a variety of self-supervised tasks with labels inherent  ...  We introduce novel domain specific self-supervision tasks that leverage contextual, multi-resolution and semantic features in pathology images for semi-supervised learning and domain adaptation.  ...  We define v as a vector of image orders in a 2×2 grids where each grid includes a specific magnification.  ... 
arXiv:2008.05571v1 fatcat:tbgp42venreotlofe2fien4jhu

Self-EMD: Self-Supervised Object Detection without ImageNet [article]

Songtao Liu, Zeming Li, Jian Sun
2021 arXiv   pre-print
In this paper, we propose a novel self-supervised representation learning method, Self-EMD, for object detection.  ...  Our Faster R-CNN (ResNet50-FPN) baseline achieves 39.8% mAP on COCO, which is on par with the state of the art self-supervised methods pre-trained on ImageNet.  ...  All results are based on the same Faster R-CNN with a ResNet50 backbone and a FPN neck. Figure 3 . 3 The framework of self-supervised methods.  ... 
arXiv:2011.13677v3 fatcat:2dv6eda335gltpnlz2cgv6bkpu

Self-Adversarial Disentangling for Specific Domain Adaptation [article]

Qianyu Zhou, Qiqi Gu, Jiangmiao Pang, Zhengyang Feng, Guangliang Cheng, Xuequan Lu, Jianping Shi, Lizhuang Ma
2021 arXiv   pre-print
., numerical magnitudes of this dimension) is crucial when adapting to a specific domain. To address the problem, we propose a novel Self-Adversarial Disentangling (SAD) framework.  ...  Our method can be easily taken as a plug-and-play framework and does not introduce any extra costs in the inference time.  ...  We propose a novel self-adversarial disentangling framework by leveraging the explicit prior domain knowledge to learn the domainness-invariant features. 2) We present a domainness creator for specifically  ... 
arXiv:2108.03553v2 fatcat:ce4hubfkf5ga7ee2xdxhojhwiq

Rectifying Self Organizing Maps for Automatic Concept Learning from Web Images [article]

Eren Golge, Pinar Duygulu
2013 arXiv   pre-print
We propose a novel clustering and outlier detection method, namely Rectifying Self Organizing Maps (RSOM).  ...  The idea is based on discovering common characteristics shared among subsets of images by posing a method that is able to organise the data while eliminating irrelevant instances.  ...  Overview of the RSOM framework for concept learning.  ... 
arXiv:1312.4384v1 fatcat:bvwu47eilrfr7hp2gmlsblwxdm

Self-supervised learning for specified latent representation

ChiCheng Liu, Libin Song, Jiwen Zhang, Ken Chen, Jing Xu
2019 IEEE transactions on fuzzy systems  
Second, a self-learning method using structured unlabeled samples is proposed to shape the free space between the framework nodes in the latent space.  ...  To this end, this paper attempts to propose a specified latent representation with physical semantic meaning.  ...  To format the framework of the latent space for the semantics and reduce the number of labeled samples, supervised learning and the proposed self-supervised learning technique are combined in this paper  ... 
doi:10.1109/tfuzz.2019.2904237 fatcat:praia4n2qndddol4j3hgqtaar4

SESS: Self-Ensembling Semi-Supervised 3D Object Detection [article]

Na Zhao, Tat-Seng Chua, Gim Hee Lee
2021 arXiv   pre-print
Inspired by the recent success of self-ensembling technique in semi-supervised image classification task, we propose SESS, a self-ensembling semi-supervised 3D object detection framework.  ...  Semi-supervised learning is a good alternative to mitigate the data annotation issue, but has remained largely unexplored in 3D object detection.  ...  Conclusion In this paper, we propose SESS, a novel self-ensembling semi-supervised point cloud-based 3D object detection framework.  ... 
arXiv:1912.11803v3 fatcat:7tmdcso3bbfcpobzjho2hlhega

SCOPS: Self-Supervised Co-Part Segmentation [article]

Wei-Chih Hung, Varun Jampani, Sifei Liu, Pavlo Molchanov, Ming-Hsuan Yang, Jan Kautz
2019 arXiv   pre-print
We propose a self-supervised deep learning approach for part segmentation, where we devise several loss functions that aids in predicting part segments that are geometrically concentrated, robust to object  ...  instances compared to existing self-supervised techniques.  ...  In this work, we propose a self-supervised deep learning framework for part segmentation.  ... 
arXiv:1905.01298v1 fatcat:lr7j7an45rbvzb2tgvympp66gi

SEAL: Self-supervised Embodied Active Learning using Exploration and 3D Consistency [article]

Devendra Singh Chaplot, Murtaza Dalal, Saurabh Gupta, Jitendra Malik, Ruslan Salakhutdinov
2021 arXiv   pre-print
We build and utilize 3D semantic maps to learn both action and perception in a completely self-supervised manner.  ...  We present a framework called Self-supervised Embodied Active Learning (SEAL). It utilizes perception models trained on internet images to learn an active exploration policy.  ...  cloud (GPC) using x et G 5: Compute semantic obs S e t as f P ;θ (I e t ) 6: Compute semantic features f e t : AveragePool (S e t ) 7: Convert GPC into voxel grid and fill with f e t : mt 8: m t = max  ... 
arXiv:2112.01001v1 fatcat:5vvysf4wjvc5pptvdtkvjqkmne
« Previous Showing results 1 — 15 out of 19,940 results