{"_id":"7tyFJdBkJvtTZWkQM","bibbaseid":"souza-zanchettin-improvingdeepimageclusteringwithspatialtransformerlayers-2019","authorIDs":["PtDsdiZ3iPSFZKH6J"],"author_short":["Souza, T.","Zanchettin, C."],"bibdata":{"title":"Improving deep image clustering with spatial transformer layers","type":"misc","year":"2019","source":"arXiv","keywords":"Adaptive Clustering,Deep Neural Networks,Image Clustering,Spatial Transformer Networks,Visual Attention","id":"482d1a61-81cb-366c-9867-009002e9784c","created":"2020-10-28T23:59:00.000Z","file_attached":false,"profile_id":"74e7d4ea-3dac-3118-aab9-511a5b337e8f","last_modified":"2020-10-31T22:01:52.735Z","read":false,"starred":false,"authored":"true","confirmed":false,"hidden":false,"private_publication":false,"abstract":"Copyright © 2019, arXiv, All rights reserved. Image clustering is an important but challenging task in machine learning. As in most image processing areas, the latest improvements came from models based on the deep learning approach. However, classical deep learning methods have problems to deal with spatial image transformations like scale and rotation. In this paper, we propose the use of visual attention techniques to reduce this problem in image clustering methods. We evaluate the combination of a deep image clustering model called Deep Adaptive Clustering (DAC) with the Spatial Transformer Networks (STN). The proposed model is evaluated in the datasets MNIST and FashionMNIST and outperformed the baseline model.","bibtype":"misc","author":"Souza, T.V.M. and Zanchettin, C.","bibtex":"@misc{\n title = {Improving deep image clustering with spatial transformer layers},\n type = {misc},\n year = {2019},\n source = {arXiv},\n keywords = {Adaptive Clustering,Deep Neural Networks,Image Clustering,Spatial Transformer Networks,Visual Attention},\n id = {482d1a61-81cb-366c-9867-009002e9784c},\n created = {2020-10-28T23:59:00.000Z},\n file_attached = {false},\n profile_id = {74e7d4ea-3dac-3118-aab9-511a5b337e8f},\n last_modified = {2020-10-31T22:01:52.735Z},\n read = {false},\n starred = {false},\n authored = {true},\n confirmed = {false},\n hidden = {false},\n private_publication = {false},\n abstract = {Copyright © 2019, arXiv, All rights reserved. Image clustering is an important but challenging task in machine learning. As in most image processing areas, the latest improvements came from models based on the deep learning approach. However, classical deep learning methods have problems to deal with spatial image transformations like scale and rotation. In this paper, we propose the use of visual attention techniques to reduce this problem in image clustering methods. We evaluate the combination of a deep image clustering model called Deep Adaptive Clustering (DAC) with the Spatial Transformer Networks (STN). The proposed model is evaluated in the datasets MNIST and FashionMNIST and outperformed the baseline model.},\n bibtype = {misc},\n author = {Souza, T.V.M. and Zanchettin, C.}\n}","author_short":["Souza, T.","Zanchettin, C."],"biburl":"https://bibbase.org/service/mendeley/74e7d4ea-3dac-3118-aab9-511a5b337e8f","bibbaseid":"souza-zanchettin-improvingdeepimageclusteringwithspatialtransformerlayers-2019","role":"author","urls":{},"keyword":["Adaptive Clustering","Deep Neural Networks","Image Clustering","Spatial Transformer Networks","Visual Attention"],"metadata":{"authorlinks":{"zanchettin, c":"https://zanche.github.io/publications/"}},"downloads":2},"bibtype":"misc","biburl":"https://bibbase.org/service/mendeley/74e7d4ea-3dac-3118-aab9-511a5b337e8f","creationDate":"2020-09-20T18:31:42.358Z","downloads":2,"keywords":["adaptive clustering","deep neural networks","image clustering","spatial transformer networks","visual attention"],"search_terms":["improving","deep","image","clustering","spatial","transformer","layers","souza","zanchettin"],"title":"Improving deep image clustering with spatial transformer layers","year":2019,"dataSources":["fvRdkx56Jpp5ebtSw","XkGKCoQgZDKqXZqdh","ya2CyA73rpZseyrZ8","2252seNhipfTmjEBQ"]}