Convolutional Sparse Autoencoders for Image Classification

Luo, Wei; Li, Jun; Yang, Jian; Xu, Wei; Zhang, Jian

doi:10.1109/tnnls.2017.2712793

Cited by 89 publications

(41 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our approach could classify images at the highest accuracy. Although the computational complexity of our approach is much lower than deep learning methods, the accuracy of our method is higher than deep learning method reported in [24] and equal to deep learning method reported in [25], which shows advantage of our method in both reducing computational cost and increasing accuracy. [13] 67.0% 73.2% LLC [14] 65.4% 73.4% Local Pooling [26] -77.3% GLP [27] 70.3% 82.7% DASDL p [28] -75.5% N 3 SC encoder [29] 67.5% 73.9% FScSPM (Our Approach) 76.3% 84.8% Table 3.…”

Section: Caltech-101 Datasetmentioning

confidence: 80%

A Fast Sparse Coding Method for Image Classification

et al. 2019

View full text Add to dashboard Cite

Image classification is an important problem in computer vision. The sparse coding spatial pyramid matching (ScSPM) framework is widely used in this field. However, the sparse coding cannot effectively handle very large training sets because of its high computational complexity, and ignoring the mutual dependence among local features results in highly variable sparse codes even for similar features. To overcome the shortcomings of previous sparse coding algorithm, we present an image classification method, which replaces the sparse dictionary with a stable dictionary learned via low computational complexity clustering, more specifically, a k-medoids cluster method optimized by k-means++. The proposed method can reduce the learning complexity and improve the feature’s stability. In the experiments, we compared the effectiveness of our method with the existing ScSPM method and its improved versions. We evaluated our approach on two diverse datasets: Caltech-101 and UIUC-Sports. The results show that our method can increase the accuracy of spatial pyramid matching, which suggests that our method is capable of improving performance of sparse coding features.

show abstract

Section: Caltech-101 Datasetmentioning

confidence: 80%

A Fast Sparse Coding Method for Image Classification

et al. 2019

View full text Add to dashboard Cite

show abstract

“…The differences between the other CSC-based methods (Chen, Li, Ma, & Wei, 2016;Luo et al, 2017;Yu & Sun, 2017) and the proposed method are described below. In the method proposed by Chen et al, filters are constructed for each class using training data.…”

Section: Test Phase Of Csdrnmentioning

confidence: 99%

“…However, since the proposed method enables input features to be adaptively determined from input images, the obtained results are robust. Luo et al (2017) achieved a reduction in computational costs by using a convolutional sparse autoencoder, which is proposed in their paper. Moreover, dictionaries calculated via CSC were set to the initial filters of a two-or three-layered CNN, and they examined the use of a combination of CNN and CSC.…”

Section: Test Phase Of Csdrnmentioning

confidence: 99%

Convolutional sparse coding‐based deep random vector functional link network for distress classification of road structures

Maeda

Takahashi

Ogawa

et al. 2019

Computer aided Civil Eng

View full text Add to dashboard Cite

This paper presents a convolutional sparse coding (CSC)‐based deep random vector functional link network (CSDRN) for distress classification of road structures. The main contribution of this paper is the introduction of CSC into a feature extraction scheme in the distress classification. CSC can extract visual features representing characteristics of target images because it can successfully estimate optimal convolutional dictionary filters and sparse features as visual features by training from a small number of distress images. The optimal dictionaries trained from distress images have basic components of visual characteristics such as edge and line information of distress images. Furthermore, sparse feature maps estimated on the basis of the dictionaries represent both strength of the basic components and location information of regions having their components, and these maps can represent distress images. That is, sparse feature maps can extract key components from distress images that have diverse visual characteristics. Therefore, CSC‐based feature extraction is effective for training from a limited number of distress images that have diverse visual characteristics. The construction of a novel neural network, CSDRN, by the use of a combination of CSC‐based feature extraction and the DRN classifier, which can also be trained from a small dataset, is shown in this paper. Accurate distress classification is realized via the CSDRN.

show abstract

“…Convolutional sparse coding (CSC) and convolutional auto-encoders (CAEs) extend the original patch-based models to cope with multidimensional and large-sized images. Both have performed well in natural image reconstruction, denoising, and classification [16,17]. CAEs, in particular, can learn global structures, using multidimensional filters with convolutional operation, and unlike patch-based methods, they preserve the relationships between neighbourhood and spatial information.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Deep Transfer Feature Learning for Medical Image Classification

Ahn

Kumar

Feng

et al. 2019

2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019)

View full text Add to dashboard Cite

The accuracy and robustness of image classification with supervised deep learning are dependent on the availability of large-scale, annotated training data. However, there is a paucity of annotated data available due to the complexity of manual annotation. To overcome this problem, a popular approach is to use transferable knowledge across different domains by: 1) using a generic feature extractor that has been pre-trained on large-scale general images (i.e., transferlearned) but which not suited to capture characteristics from medical images; or 2) fine-tuning generic knowledge with a relatively smaller number of annotated images. Our aim is to reduce the reliance on annotated training data by using a new hierarchical unsupervised feature extractor with a convolutional auto-encoder placed atop of a pre-trained convolutional neural network. Our approach constrains the rich and generic image features from the pre-trained domain to a sophisticated representation of the local image characteristics from the unannotated medical image domain. Our approach has a higher classification accuracy than transfer-learned approaches and is competitive with state-ofthe-art supervised fine-tuned methods.

show abstract

Convolutional Sparse Autoencoders for Image Classification

Cited by 89 publications

References 19 publications

A Fast Sparse Coding Method for Image Classification

A Fast Sparse Coding Method for Image Classification

Convolutional sparse coding‐based deep random vector functional link network for distress classification of road structures

Unsupervised Deep Transfer Feature Learning for Medical Image Classification

Contact Info

Product

Resources

About