Rotation, Scaling and Deformation Invariant Scattering for Texture Discrimination

Sifre, Laurent; Mallat, Stéphane

doi:10.1109/cvpr.2013.163

Cited by 360 publications

(329 citation statements)

References 16 publications

Supporting

Mentioning

310

Contrasting

Order By: Relevance

“…Bruna et al (2013) define convolution operations over arbitrary graphs, generalizing from the typical grid of pixels to other locally connected structures. Sifre & Mallat (2013) extract representations that are invariant to affine transformations, based on scattering transforms. However, these representations are fixed (i.e., not learned from data), and not specifically tuned for the task at hand, unlike the representations learned by convolutional neural networks.…”

Section: Related Workmentioning

confidence: 99%

Rotation-invariant convolutional neural networks for galaxy morphology prediction

Dieleman¹,

Willett²,

Dambre³

2015

Monthly Notices of the Royal Astronomical Society

712

604

View full text Add to dashboard Cite

Measuring the morphological parameters of galaxies is a key requirement for studying their formation and evolution. Surveys such as the Sloan Digital Sky Survey (SDSS) have resulted in the availability of very large collections of images, which have permitted population-wide analyses of galaxy morphology. Morphological analysis has traditionally been carried out mostly via visual inspection by trained experts, which is time-consuming and does not scale to large ( 10 4 ) numbers of images.Although attempts have been made to build automated classification systems, these have not been able to achieve the desired level of accuracy. The Galaxy Zoo project successfully applied a crowdsourcing strategy, inviting online users to classify images by answering a series of questions. Unfortunately, even this approach does not scale well enough to keep up with the increasing availability of galaxy images.We present a deep neural network model for galaxy morphology classification which exploits translational and rotational symmetry. It was developed in the context of the Galaxy Challenge, an international competition to build the best model for morphology classification based on annotated images from the Galaxy Zoo project.For images with high agreement among the Galaxy Zoo participants, our model is able to reproduce their consensus with near-perfect accuracy (> 99%) for most questions. Confident model predictions are highly accurate, which makes the model suitable for filtering large collections of images and forwarding challenging images to experts for manual annotation. This approach greatly reduces the experts' workload without affecting accuracy. The application of these algorithms to larger sets of training data will be critical for analysing results from future surveys such as the LSST.

show abstract

Section: Related Workmentioning

confidence: 99%

Rotation-invariant convolutional neural networks for galaxy morphology prediction

Dieleman¹,

Willett²,

Dambre³

2015

Monthly Notices of the Royal Astronomical Society

712

604

View full text Add to dashboard Cite

show abstract

“…Specifically, Xception's architecture is constructed based on a linear stack of a depth-wise separable convolution layer (i.e., 36 convolutional layers) with linear residual connections (see Figure 4). There are two important convolutional layers in this configuration: A depth-wise convolutional layer [37], where a spatial convolution is carried out independently in each channel of input data, and a pointwise convolutional layer, where a 1 × 1 convolutional layer maps the output channels to a new channel space using a depth-wise convolution. …”

Section: Xceptionmentioning

confidence: 99%

Very Deep Convolutional Neural Networks for Complex Land Cover Mapping Using Multispectral Remote Sensing Imagery

et al. 2018

View full text Add to dashboard Cite

Despite recent advances of deep Convolutional Neural Networks (CNNs) in various computer vision tasks, their potential for classification of multispectral remote sensing images has not been thoroughly explored. In particular, the applications of deep CNNs using optical remote sensing data have focused on the classification of very high-resolution aerial and satellite data, owing to the similarity of these data to the large datasets in computer vision. Accordingly, this study presents a detailed investigation of state-of-the-art deep learning tools for classification of complex wetland classes using multispectral RapidEye optical imagery. Specifically, we examine the capacity of seven well-known deep convnets, namely DenseNet121, InceptionV3, VGG16, VGG19, Xception, ResNet50, and InceptionResNetV2, for wetland mapping in Canada. In addition, the classification results obtained from deep CNNs are compared with those based on conventional machine learning tools, including Random Forest and Support Vector Machine, to further evaluate the efficiency of the former to classify wetlands. The results illustrate that the full-training of convnets using five spectral bands outperforms the other strategies for all convnets. InceptionResNetV2, ResNet50, and Xception are distinguished as the top three convnets, providing state-of-the-art classification accuracies of 96.17%, 94.81%, and 93.57%, respectively. The classification accuracies obtained using Support Vector Machine (SVM) and Random Forest (RF) are 74.89% and 76.08%, respectively, considerably inferior relative to CNNs. Importantly, InceptionResNetV2 is consistently found to be superior compared to all other convnets, suggesting the integration of Inception and ResNet modules is an efficient architecture for classifying complex remote sensing scenes such as wetlands.

show abstract

“…In this paper, we aim to improve the robustness of scene categorization by removing the distortions caused by arbitrary affine transformations. Because the (general) projective transformation can be locally approximated by affine transformations [6], the approach presented here constitutes a step towards developing a view-invariant scene categorization system.…”

Section: Introductionmentioning

confidence: 99%

Affine-invariant scene categorization

Xue

Phung

Bouzerdoum

2014

2014 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

This paper presents a scene categorization method that is invariant to affine transformations. We propose a new moment-based normalization algorithm to generate an output image that is independent of the position, rotation, shear, and scale of the input image. In the proposed approach, an affine transform matrix is determined subject to the normalized image satisfying a set of moment constraints. After image normalization, a dense set of local features is extracted using scattering transform, and the global features are then formed via a sparse coding method. We evaluate the proposed method and other state-of-the-art algorithms on a benchmark dataset. The experimental results show that for images distorted with affine transformations, the proposed normalization increases the classification rate by about 28%, compared with the scene categorization approach that uses no normalization. AFFINE-INVARIANT SCENE CATEGORIZATION Xue Wei, Son Lam Phung, and Abdesselam Bouzerdoum School of Electrical, Computer and Telecommunication EngineeringUniversity of Wollongong, NSW, Australia, 2522 Email: xw158@uowmail.edu.au, phung@uow.edu.au, and bouzer@uow.edu.au ABSTRACT This paper presents a scene categorization method that is invariant to affine transformations. We propose a new momentbased normalization algorithm to generate an output image that is independent of the position, rotation, shear, and scale of the input image. In the proposed approach, an affine transform matrix is determined subject to the normalized image satisfying a set of moment constraints. After image normalization, a dense set of local features is extracted using scattering transform, and the global features are then formed via a sparse coding method. We evaluate the proposed method and other state-of-the-art algorithms on a benchmark dataset. The experimental results show that for images distorted with affine transformations, the proposed normalization increases the classification rate by about 28%, compared with the scene categorization approach that uses no normalization.

show abstract

Rotation, Scaling and Deformation Invariant Scattering for Texture Discrimination

Cited by 360 publications

References 16 publications

Rotation-invariant convolutional neural networks for galaxy morphology prediction

Rotation-invariant convolutional neural networks for galaxy morphology prediction

Very Deep Convolutional Neural Networks for Complex Land Cover Mapping Using Multispectral Remote Sensing Imagery

Affine-invariant scene categorization

Contact Info

Product

Resources

About