Filters








15,017 Hits in 2.5 sec

Grapy-ML: Graph Pyramid Mutual Learning for Cross-Dataset Human Parsing

Haoyu He, Jing Zhang, Qiming Zhang, Dacheng Tao
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
Starting from the prior knowledge of the human body hierarchical structure, we devise a graph pyramid module (GPM) by stacking three levels of graph structures from coarse granularity to fine granularity  ...  Then, it adopts a top-down mechanism to progressively refine the hierarchical features through all the levels. GPM also enables efficient mutual learning.  ...  : 1) hierarchical structure modeling; 2) multi-task learning and transfer learning.  ... 
doi:10.1609/aaai.v34i07.6728 fatcat:juvtu6haingcxgoaabsydtbfaa

Grapy-ML: Graph Pyramid Mutual Learning for Cross-dataset Human Parsing [article]

Haoyu He, Jing Zhang, Qiming Zhang, Dacheng Tao
2019 arXiv   pre-print
Starting from the prior knowledge of the human body hierarchical structure, we devise a graph pyramid module (GPM) by stacking three levels of graph structures from coarse granularity to fine granularity  ...  Then, it adopts a top-down mechanism to progressively refine the hierarchical features through all the levels. GPM also enables efficient mutual learning.  ...  : 1) hierarchical structure modeling; 2) multi-task learning and transfer learning.  ... 
arXiv:1911.12053v1 fatcat:ugfuo5dp35hr7i5lpkrnrhfc6m

Graphonomy: Universal Human Parsing via Graph Transfer Learning

Ke Gong, Yiming Gao, Xiaodan Liang, Xiaohui Shen, Meng Wang, Liang Lin
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
This poses many fundamental learning challenges, e.g. discovering underlying semantic structures among different label granularity, performing proper transfer learning across different image domains, and  ...  To address these challenges, we propose a new universal human parsing agent, named "Graphonomy", which incorporates hierarchical graph transfer learning upon the conventional parsing network to encode  ...  The part labels among them are hierarchically correlated and the label granularity is from coarse to fine.  ... 
doi:10.1109/cvpr.2019.00763 dblp:conf/cvpr/Gong0LS0L19 fatcat:rv5xgqag4jcghmzffi3s67fp2u

Graphonomy: Universal Human Parsing via Graph Transfer Learning [article]

Ke Gong, Yiming Gao, Xiaodan Liang, Xiaohui Shen, Meng Wang, Liang Lin
2019 arXiv   pre-print
This poses many fundamental learning challenges, e.g. discovering underlying semantic structures among different label granularity, performing proper transfer learning across different image domains, and  ...  To address these challenges, we propose a new universal human parsing agent, named "Graphonomy", which incorporates hierarchical graph transfer learning upon the conventional parsing network to encode  ...  The part labels among them are hierarchically correlated and the label granularity is from coarse to fine.  ... 
arXiv:1904.04536v1 fatcat:di2yce3ytbhadml5lljt7yn66m

MGFN: A Multi-Granularity Fusion Convolutional Neural Network for Remote Sensing Scene Classification

Zhiguo Zeng, Xihong Chen, Zhihua Song
2021 IEEE Access  
Additionally, Cheng verified the power of fine-tuning transfer learning on a new remote sensing scene dataset [21] .  ...  PROPOSED MGFN ARCHITECTURE The core idea of the proposed MGFN is granularly learning hierarchical features to reduce visual-semantic discrepancies and then fusing multiple granularities with emphasis on  ... 
doi:10.1109/access.2021.3081922 fatcat:lnabnm7zung3jadqzkcusq3m3q

Misc-GAN: A Multi-scale Generative Model for Graphs

Dawei Zhou, Lecheng Zheng, Jiejun Xu, Jingrui He
2019 Frontiers in Big Data  
In this paper, we propose a multi-scale graph generative model named Misc-GAN, which models the underlying distribution of graph structures at different levels of granularity, and then "transfers" such  ...  hierarchical distribution from the graphs in the domain of interest, to a unique graph representation.  ...  ., 2017 ) is adopted to learn the graph structure distribution and generate a synthetic coarse graph at each granularity level.  ... 
doi:10.3389/fdata.2019.00003 pmid:33693326 pmcid:PMC7931912 fatcat:jciqxestzbag5ibq6n437t52ee

Label Relation Graphs Enhanced Hierarchical Residual Network for Hierarchical Multi-Granularity Classification [article]

Jingzhou Chen, Peng Wang, Jian Liu, Yuntao Qian
2022 arXiv   pre-print
The essential designs of the proposed method are derived from two motivations: (1) learning with objects labeled at various levels should transfer hierarchical knowledge between levels; (2) lower-level  ...  Hierarchical multi-granularity classification (HMC) assigns hierarchical multi-granularity labels to each object and focuses on encoding the label hierarchy, e.g., ["Albatross", "Laysan Albatross"] from  ...  Visualization Experiments We conduct visualization experiments to demonstrate that granularity-specific blocks can capture different regions of interest while hierarchical knowledge can be transferred  ... 
arXiv:2201.03194v2 fatcat:vwnkqsqnhjbqbfqpszeyrwwilu

Learning Multi-Granularity Neural Network Encoding Image Classification Using DCNNs for Easter Africa Community Countries

Musabe Jean Bosco, Guoyin Wang, Yves Hategekimana
2021 IEEE Access  
INDEX TERMS Convolutional neural networks (CNNs), fine-tuning, granularity feature extraction, machine learning, and remote sensing (RS).  ...  Training deep learning model-based approaches has to do with scene classification and brings about fantastic achievement.  ...  In the second phase, we introduce transfer learning approaches; for learning features such as colors, edges, and shapes. 2) The fine-trained multi-granularity level through the multi-granularity level  ... 
doi:10.1109/access.2021.3122569 fatcat:arizvsrcnjbxxlclzrcvtep42a

Special issue on challenges in knowledge discovery and data mining

Shusaku Tsumoto
2013 Journal of Intelligent Information Systems  
The second paper, entitled Transfer Learning by Centroid Pivoted Mapping in Noisy Environment, written by Thach Nguyen Huy, Bin Tong, Hao Shao, and Einoshin Suzuki proposes a new approach to transfer learning  ...  learning, clustering, mining on multi-granularity level (application), and sensor data mining.  ... 
doi:10.1007/s10844-013-0261-8 fatcat:74knmysaz5cktmch2gzpojjnzi

Multi-view Hierarchical Clustering [article]

Qinghai Zheng, Jihua Zhu, Shuangxun Ma
2020 arXiv   pre-print
To overcome these limitations, we propose a Multi-view Hierarchical Clustering (MHC), which partitions multi-view data recursively at multiple levels of granularity.  ...  The CDI can explore the underlying complementary information of multi-view data so as to learn an essential distance matrix, which is utilized in NNA to obtain the clustering results.  ...  Hierarchical Clustering Hierarchical clustering is a clustering method which clusters data samples at multiple levels of granularity [16, 19, 20, 21] .  ... 
arXiv:2010.07573v1 fatcat:errcr2647vaddh5aswjpkqm7ym

Hierarchical Learning for Modular Robots [article]

Risto Kojcev, Nora Etxezarreta, Alejandro Hernández, Víctor Mayoral
2018 arXiv   pre-print
We present a hierarchical approach for modular robots that allows a robot to simultaneously learn multiple tasks.  ...  The trained neural network is then transferred and executed on a real robot with 3DoF and 4DoF configurations.  ...  tasks and low transfer capabilities between related tasks.  ... 
arXiv:1802.04132v1 fatcat:oqb5b377sbhkdorrmofbb4u5yi

Leveraging cognitive context knowledge for argumentation based object classification in multi-sensor networks

Zhiyong Hao, Junfeng Wu, Tingting Liu, Xiaohong Chen
2019 IEEE Access  
To address this category of granularity inconsistent problem in multi-sensor collaborative object classification tasks, we propose a cognitive context knowledge-enriched method for classification conflict  ...  Following the description of subsection B, multi-granular classification rules can be learned hierarchically from the training datasets, referring to the category taxonomy Ta, which obtained from domain  ...  Our proposed algorithm for learning multi-granular classification rules is described in TABLE 3.  ... 
doi:10.1109/access.2019.2919073 fatcat:azmkmxylcneppjga45mct7nmcq

Hierarchical Relation-Guided Type-Sentence Alignment for Long-Tail Relation Extraction with Distant Supervision [article]

Yang Li, Guodong Long, Tao Shen, Jing Jiang
2021 arXiv   pre-print
Some works use the hierarchy of relations for knowledge transfer to long-tail relations.  ...  One solution is resorting to entity types, but open questions remain about how to fully leverage the information of entity types and how to align multi-granular entity types with sentences.  ...  Knowledge transfer via hierarchical relations is effective.  ... 
arXiv:2109.09036v1 fatcat:h2dsow3xebgpfgmhgawdrbj5he

Progressive One-shot Human Parsing [article]

Haoyu He, Jing Zhang, Bhavani Thuraisingham, Dacheng Tao
2021 arXiv   pre-print
POPNet consists of two collaborative metric learning modules named Attention Guidance Module and Nearest Centroid Module, which can learn representative prototypes for base classes and quickly transfer  ...  Moreover, POPNet adopts a progressive human parsing framework that can incorporate the learned knowledge of parent classes at the coarse granularity to help recognize the descendant classes at the fine  ...  In this spirit, we also use a hierarchical structure in our POPNet to leverage the learned knowledge at the coarse granularity to aid the learning process at the fine granularity, thereby enhancing the  ... 
arXiv:2012.11810v3 fatcat:c3nuadbx4jgsli6bsmcznnbpwa

Learning to Forecast Videos of Human Activity with Multi-granularity Models and Adaptive Rendering [article]

Mengyao Zhai, Jiacheng Chen, Ruizhi Deng, Lei Chen, Ligeng Zhu, Greg Mori
2017 arXiv   pre-print
Next, our appearance rendering network encodes the targets' appearances by learning adaptive appearance filters using a fully convolutional network.  ...  Our hierarchical model captures interactions among people by adopting a dynamic group-based interaction mechanism.  ...  To transfer the desired appearance to the encoderdecoder branch, we replace the last convolutional filter in the encoder-decoder branch with our adaptive appearance transfer filter.  ... 
arXiv:1712.01955v1 fatcat:22a5mvzl55g4bdbjj367jup22e
« Previous Showing results 1 — 15 out of 15,017 results