Recursive Autoconvolution for Unsupervised Learning of Convolutional Neural Networks
In visual recognition tasks, such as image classification, unsupervised learning exploits cheap unlabeled data and can help to solve these tasks more efficiently. We show that the recursive autoconvolution operator, adopted from physics, boosts existing unsupervised methods by learning more discriminative filters. We take well established convolutional neural networks and train their filters layer-wise. In addition, based on previous works we design a network which extracts more than 600k features per sample, but with the total number of trainable parameters greatly reduced by introducing shared filters in higher layers. We evaluate our networks on the MNIST, CIFAR-10, CIFAR-100 and STL-10 image classification benchmarks and report several state of the art results among other unsupervised methods.
Code (2)
Tasks
ClassificationGeneral Classificationimage-classificationImage ClassificationSimilar Papers 제목 키워드 기반
Grokability in five inequalities
In this note, we report five mathematical discoveries made in collaboration with Grok, all of which have been subsequently verified by the authors. These include an improved lower bound on the maximal Gaussian perimeter …
SumGraph: Video Summarization via Recursive Graph Modeling
The goal of video summarization is to select keyframes that are visually diverse and can represent a whole story of an input video. State-of-the-art approaches for video summarization have mostly regarded the task as a f…
Video SummarizationRecursive Cascaded Networks for Unsupervised Medical Image Registration
We present recursive cascaded networks, a general architecture that enables learning deep cascades, for deformable image registration. The proposed architecture is simple in design and can be built on any base network. T…
Image RegistrationMedical Image RegistrationDeeply-Recursive Convolutional Network for Image Super-Resolution
We propose an image super-resolution method (SR) using a deeply-recursive convolutional network (DRCN). Our network has a very deep recursive layer (up to 16 recursions). Increasing recursion depth can improve performanc…
Image Super-ResolutionSuper-ResolutionUnsupervised Latent Tree Induction with Deep Inside-Outside Recursive Auto-Encoders
We introduce the deep inside-outside recursive autoencoder (DIORA), a fully-unsupervised method for discovering syntax that simultaneously learns representations for constituents within the induced tree. Our approach pre…
Constituency Grammar InductionConstituency ParsingSentence