paper-with-me

Papers

Stacked What-Where Auto-encoders

2015-06-08 · Junbo Zhao, Michael Mathieu, Ross Goroshin, Yann Lecun

We present a novel architecture, the "stacked what-where auto-encoders" (SWWAE), which integrates discriminative and generative pathways and provides a unified approach to supervised, semi-supervised and unsupervised learning without relying on sampling during training. An instantiation of SWWAE uses a convolutional net (Convnet) (LeCun et al. (1998)) to encode the input, and employs a deconvolutional net (Deconvnet) (Zeiler et al. (2010)) to produce the reconstruction. The objective function includes reconstruction terms that induce the hidden states in the Deconvnet to be similar to those of the Convnet. Each pooling layer produces two sets of variables: the "what" which are fed to the next layer, and its complementary variable "where" that are fed to the corresponding layer in the generative decoder.

📄 PDF Abstract BibTeX arXiv:1506.02351

Code (2)

isaacgerg/keras_odds_and_ends tf
zhangqinghao0811/unpool tf

Tasks

DecoderImage ClassificationSemi-Supervised Image Classification

Similar Papers 제목 키워드 기반

Gradual training of deep denoising auto encoders

2014-12-19 · Alexander Kalmanovich, Gal Chechik

Stacked denoising auto encoders (DAEs) are well known to learn useful deep representations, which can be used to improve supervised training by initializing a deep network. We investigate a training scheme of a deep DAE,…

DenoisingGeneral Classification

Gradual Training Method for Denoising Auto Encoders

2015-04-11 · Alexander Kalmanovich, Gal Chechik

Stacked denoising auto encoders (DAEs) are well known to learn useful deep representations, which can be used to improve supervised training by initializing a deep network. We investigate a training scheme of a deep DAE,…

DenoisingGeneral Classification

Remote sensing framework for geological mapping via stacked autoencoders and clustering

2024-04-02 · Sandeep Nagar, Ehsan Farahbakhsh, Joseph Awange, Rohitash Chandra

Supervised machine learning methods for geological mapping via remote sensing face limitations due to the scarcity of accurately labelled training data that can be addressed by unsupervised learning, such as dimensionali…

ClusteringDimensionality Reduction

Stacked Autoencoders for Medical Image Search

2016-10-02 · S. Sharma, I. Umar, L. Ospina, D. Wong 외

Medical images can be a valuable resource for reliable information to support medical diagnosis. However, the large volume of medical images makes it challenging to retrieve relevant information given a particular scenar…

Content-Based Image RetrievalImage RetrievalMedical DiagnosisRetrieval

Training Stacked Denoising Autoencoders for Representation Learning

2021-02-16 · Jason Liang, Keith Kelly

We implement stacked denoising autoencoders, a class of neural networks that are capable of learning powerful representations of high dimensional data. We describe stochastic gradient descent for unsupervised training of…

Denoisingimage-classificationImage ClassificationRepresentation Learning