@InProceedings{8902831,
  author = {M. Ulicny and V. A. Krylov and R. Dahyot},
  booktitle = {2019 27th European Signal Processing Conference (EUSIPCO)},
  title = {Harmonic Networks with Limited Training Samples},
  year = {2019},
  pages = {1-5},
  abstract = {Convolutional neural networks (CNNs) are very popular nowadays for image processing. CNNs allow one to learn optimal filters in a (mostly) supervised machine learning context. However this typically requires abundant labelled training data to estimate the filter parameters. Alternative strategies have been deployed for reducing the number of parameters and / or filters to be learned and thus decrease overfitting. In the context of reverting to preset filters, we propose here a computationally efficient harmonic block that uses Discrete Cosine Transform (DCT) filters in CNNs. In this work we examine the performance of harmonic networks in limited training data scenario. We validate experimentally that its performance compares well against scattering networks that use wavelets as preset filters.},
  keywords = {convolutional neural nets;discrete cosine transforms;filtering theory;image processing;supervised learning;convolutional neural networks;CNNs;image processing;optimal filters;supervised machine learning;harmonic networks;scattering networks;discrete cosine transform filters;Discrete cosine transforms;Harmonic analysis;Convolution;Signal processing algorithms;Wavelet transforms;Europe;Lapped Discrete Cosine Transform;harmonic network;convolutional filter;limited data},
  doi = {10.23919/EUSIPCO.2019.8902831},
  issn = {2076-1465},
  month = {Sep.},
  url = {https://www.eurasip.org/proceedings/eusipco/eusipco2019/proceedings/papers/1570533913.pdf},
}

{"_id":"nLsJ7GTrNyiPdPsmh","bibbaseid":"ulicny-krylov-dahyot-harmonicnetworkswithlimitedtrainingsamples-2019","authorIDs":["6fptrFgK7WSZkf6TM"],"author_short":["Ulicny, M.","Krylov, V. A.","Dahyot, R."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["M."],"propositions":[],"lastnames":["Ulicny"],"suffixes":[]},{"firstnames":["V.","A."],"propositions":[],"lastnames":["Krylov"],"suffixes":[]},{"firstnames":["R."],"propositions":[],"lastnames":["Dahyot"],"suffixes":[]}],"booktitle":"2019 27th European Signal Processing Conference (EUSIPCO)","title":"Harmonic Networks with Limited Training Samples","year":"2019","pages":"1-5","abstract":"Convolutional neural networks (CNNs) are very popular nowadays for image processing. CNNs allow one to learn optimal filters in a (mostly) supervised machine learning context. However this typically requires abundant labelled training data to estimate the filter parameters. Alternative strategies have been deployed for reducing the number of parameters and / or filters to be learned and thus decrease overfitting. In the context of reverting to preset filters, we propose here a computationally efficient harmonic block that uses Discrete Cosine Transform (DCT) filters in CNNs. In this work we examine the performance of harmonic networks in limited training data scenario. We validate experimentally that its performance compares well against scattering networks that use wavelets as preset filters.","keywords":"convolutional neural nets;discrete cosine transforms;filtering theory;image processing;supervised learning;convolutional neural networks;CNNs;image processing;optimal filters;supervised machine learning;harmonic networks;scattering networks;discrete cosine transform filters;Discrete cosine transforms;Harmonic analysis;Convolution;Signal processing algorithms;Wavelet transforms;Europe;Lapped Discrete Cosine Transform;harmonic network;convolutional filter;limited data","doi":"10.23919/EUSIPCO.2019.8902831","issn":"2076-1465","month":"Sep.","url":"https://www.eurasip.org/proceedings/eusipco/eusipco2019/proceedings/papers/1570533913.pdf","bibtex":"@InProceedings{8902831,\n author = {M. Ulicny and V. A. Krylov and R. Dahyot},\n booktitle = {2019 27th European Signal Processing Conference (EUSIPCO)},\n title = {Harmonic Networks with Limited Training Samples},\n year = {2019},\n pages = {1-5},\n abstract = {Convolutional neural networks (CNNs) are very popular nowadays for image processing. CNNs allow one to learn optimal filters in a (mostly) supervised machine learning context. However this typically requires abundant labelled training data to estimate the filter parameters. Alternative strategies have been deployed for reducing the number of parameters and / or filters to be learned and thus decrease overfitting. In the context of reverting to preset filters, we propose here a computationally efficient harmonic block that uses Discrete Cosine Transform (DCT) filters in CNNs. In this work we examine the performance of harmonic networks in limited training data scenario. We validate experimentally that its performance compares well against scattering networks that use wavelets as preset filters.},\n keywords = {convolutional neural nets;discrete cosine transforms;filtering theory;image processing;supervised learning;convolutional neural networks;CNNs;image processing;optimal filters;supervised machine learning;harmonic networks;scattering networks;discrete cosine transform filters;Discrete cosine transforms;Harmonic analysis;Convolution;Signal processing algorithms;Wavelet transforms;Europe;Lapped Discrete Cosine Transform;harmonic network;convolutional filter;limited data},\n doi = {10.23919/EUSIPCO.2019.8902831},\n issn = {2076-1465},\n month = {Sep.},\n url = {https://www.eurasip.org/proceedings/eusipco/eusipco2019/proceedings/papers/1570533913.pdf},\n}\n\n","author_short":["Ulicny, M.","Krylov, V. A.","Dahyot, R."],"key":"8902831","id":"8902831","bibbaseid":"ulicny-krylov-dahyot-harmonicnetworkswithlimitedtrainingsamples-2019","role":"author","urls":{"Paper":"https://www.eurasip.org/proceedings/eusipco/eusipco2019/proceedings/papers/1570533913.pdf"},"keyword":["convolutional neural nets;discrete cosine transforms;filtering theory;image processing;supervised learning;convolutional neural networks;CNNs;image processing;optimal filters;supervised machine learning;harmonic networks;scattering networks;discrete cosine transform filters;Discrete cosine transforms;Harmonic analysis;Convolution;Signal processing algorithms;Wavelet transforms;Europe;Lapped Discrete Cosine Transform;harmonic network;convolutional filter;limited data"],"metadata":{"authorlinks":{"dahyot, r":"https://roznn.github.io/ipublication.html"}},"downloads":0},"bibtype":"inproceedings","biburl":"https://raw.githubusercontent.com/Roznn/EUSIPCO/main/eusipco2019url.bib","creationDate":"2021-01-17T18:19:29.523Z","downloads":0,"keywords":["convolutional neural nets;discrete cosine transforms;filtering theory;image processing;supervised learning;convolutional neural networks;cnns;image processing;optimal filters;supervised machine learning;harmonic networks;scattering networks;discrete cosine transform filters;discrete cosine transforms;harmonic analysis;convolution;signal processing algorithms;wavelet transforms;europe;lapped discrete cosine transform;harmonic network;convolutional filter;limited data"],"search_terms":["harmonic","networks","limited","training","samples","ulicny","krylov","dahyot"],"title":"Harmonic Networks with Limited Training Samples","year":2019,"dataSources":["LyGNQYGRFw8k9gPrK","NqWTiMfRR56v86wRs","dtJ7afty6nTMHhqAE","r6oz3cMyC99QfiuHW"]}