Network Deconvolution | OpenReview

Network Deconvolution Sep 25, 2019 Blind Submission readers: everyone Show Bibtex TL;DR: We propose a method called network deconvolution that resembles animal vision system to train convolution networks better. Abstract: Convolution is a central operation in Convolutional Neural Networks (CNNs), which applies a kernel to overlapping regions shifted across the image. However, because of the strong correlations in real-world image data, convolutional kernels are in effect re-learning redu

Date: 2020/05/23 12:52

Related Entries

Read more NeurIPS 2018 読み会 in 京都 [社会人枠増席] - connpass
0 users, 21 mentions 2018/12/16 15:15
Read more nlpaper.challenge NLP/CV交流勉強会 - connpass
0 users, 23 mentions 2018/12/31 09:44
Read more GitHub - takuhirok/rGAN: rGAN: Label-Noise Robust Generative Adversarial Networks
0 users, 1 mentions 2019/05/06 15:47
Read more [1811.12104] Towards Human-Friendly Referring Expression Generation
0 users, 1 mentions 2019/07/23 05:17
Read more データドリブンな仮説検証のためのSelective Inference - Speaker Deck
0 users, 1 mentions 2019/12/10 00:51