2011
DOI: 10.1007/978-3-642-21735-7_7
|View full text |Cite
|
Sign up to set email alerts
|

Stacked Convolutional Auto-Encoders for Hierarchical Feature Extraction

Abstract: Abstract. We present a novel convolutional auto-encoder (CAE) for unsupervised feature learning. A stack of CAEs forms a convolutional neural network (CNN). Each CAE is trained using conventional on-line gradient descent without additional regularization terms. A max-pooling layer is essential to learn biologically plausible features consistent with those found by previous approaches. Initializing a CNN with filters of a trained CAE stack yields superior performance on a digit (MNIST) and an object recognition… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

1
1,066
0
15

Year Published

2016
2016
2024
2024

Publication Types

Select...
6
1
1

Relationship

0
8

Authors

Journals

citations
Cited by 1,537 publications
(1,082 citation statements)
references
References 21 publications
1
1,066
0
15
Order By: Relevance
“…The hidden layer, as extracted features, were used as input data for the next encoding to acquire features in the next layer and, subsequently, the decoder was used to reconstruct the images layer by layer, starting from the bottom hidden layer. Based on SAE, SCAE changed all the input, output and the hidden layers with a one-dimension structure and used the convolution network for improved conservation of the spatial features [12]. Similar to the traditional CNN network, SCAE is the stacking of several building blocks [13], with each block containing a convolutional layer, pooling layer and a nonlinearity layer.…”
Section: Feature Extractionmentioning
confidence: 99%
“…The hidden layer, as extracted features, were used as input data for the next encoding to acquire features in the next layer and, subsequently, the decoder was used to reconstruct the images layer by layer, starting from the bottom hidden layer. Based on SAE, SCAE changed all the input, output and the hidden layers with a one-dimension structure and used the convolution network for improved conservation of the spatial features [12]. Similar to the traditional CNN network, SCAE is the stacking of several building blocks [13], with each block containing a convolutional layer, pooling layer and a nonlinearity layer.…”
Section: Feature Extractionmentioning
confidence: 99%
“…Several approaches involving the combination of these methods have been explored in the past, and here we use a CAE architecture along the lines presented in [11,18,17].…”
Section: Convolutional Autoencodersmentioning
confidence: 99%
“…The closest that unsupervised pre-training has come to FCN architectures, to the best of our knowledge, is stacked convolutional autoencoders, as defined by Mesci et al [2]. A convolutional autoencoder is a convolutional layer that is required to reconstruct its input after applying a pooling operation over its feature maps (to discourage the trivial solution), and are typically trained using the standard greedy layer-wise approach.…”
Section: Related Workmentioning
confidence: 99%
“…These transformations were possible horizontal mirroring, rotations by multiples of 10 • , and elastic deformations using parameters sampled from a continuous distribution 2 . This sampling ensures that any specific transformed image is extremely unlikely to reoccur during training, thus significantly reducing the risk of overfitting.…”
Section: Data Setmentioning
confidence: 99%
See 1 more Smart Citation