255 Hits in 1.4 sec

Unsupervised Outlier Detection using Memory and Contrastive Learning [article]

Ning Huyan, Dou Quan, Xiangrong Zhang, Xuefeng Liang, Jocelyn Chanussot, Licheng Jiao
2021 arXiv   pre-print
Outlier detection is one of the most important processes taken to create good, reliable data in machine learning. The most methods of outlier detection leverage an auxiliary reconstruction task by assuming that outliers are more difficult to be recovered than normal samples (inliers). However, it is not always true, especially for auto-encoder (AE) based models. They may recover certain outliers even outliers are not in the training data, because they do not constrain the feature learning.
more » ... ture learning. Instead, we think outlier detection can be done in the feature space by measuring the feature distance between outliers and inliers. We then propose a framework, MCOD, using a memory module and a contrastive learning module. The memory module constrains the consistency of features, which represent the normal data. The contrastive learning module learns more discriminating features, which boosts the distinction between outliers and inliers. Extensive experiments on four benchmark datasets show that our proposed MCOD achieves a considerable performance and outperforms nine state-of-the-art methods.
arXiv:2107.12642v1 fatcat:plwgvon4pvahfcj7qvf7c2blyu

Spatial-Spectral Manifold Embedding of Hyperspectral Data [article]

Danfeng Hong and Jing Yao and Xin Wu and Jocelyn Chanussot and Xiao Xiang Zhu
2020 arXiv   pre-print
In recent years, hyperspectral imaging, also known as imaging spectroscopy, has been paid an increasing interest in geoscience and remote sensing community. Hyperspectral imagery is characterized by very rich spectral information, which enables us to recognize the materials of interest lying on the surface of the Earth more easier. We have to admit, however, that high spectral dimension inevitably brings some drawbacks, such as expensive data storage and transmission, information redundancy,
more » ... tion redundancy, etc. Therefore, to reduce the spectral dimensionality effectively and learn more discriminative spectral low-dimensional embedding, in this paper we propose a novel hyperspectral embedding approach by simultaneously considering spatial and spectral information, called spatial-spectral manifold embedding (SSME). Beyond the pixel-wise spectral embedding approaches, SSME models the spatial and spectral information jointly in a patch-based fashion. SSME not only learns the spectral embedding by using the adjacency matrix obtained by similarity measurement between spectral signatures, but also models the spatial neighbours of a target pixel in hyperspectral scene by sharing the same weights (or edges) in the process of learning embedding. Classification is explored as a potential strategy to quantitatively evaluate the performance of learned embedding representations. Classification is explored as a potential application for quantitatively evaluating the performance of these hyperspectral embedding algorithms. Extensive experiments conducted on the widely-used hyperspectral datasets demonstrate the superiority and effectiveness of the proposed SSME as compared to several state-of-the-art embedding methods.
arXiv:2007.08767v1 fatcat:gytlv4whhfcrhklaiho4ernbbm

An Introduction to Deep Morphological Networks

Keiller Nogueira, Jocelyn Chanussot, Mauro Dalla Mura, Jefersson A. Dos Santos
2021 IEEE Access  
Over the past decade, Convolutional Networks (ConvNets) have renewed the perspectives of the research and industrial communities. Although this deep learning technique may be composed of multiple layers, its core operation is the convolution, an important linear filtering process. Easy and fast to implement, convolutions actually play a major role, not only in ConvNets, but in digital image processing and analysis as a whole, being effective for several tasks. However, aside from convolutions,
more » ... from convolutions, researchers also proposed and developed non-linear filters, such as operators provided by mathematical morphology. Even though these are not so computationally efficient as the linear filters, in general, they are able to capture different patterns and tackle distinct problems when compared to the convolutions. In this paper, we propose a new paradigm for deep networks where convolutions are replaced by non-linear morphological filters. Aside from performing the operation, the proposed Deep Morphological Network (DeepMorphNet) is also able to learn the morphological filters (and consequently the features) based on the input data. While this process raises challenging issues regarding training and actual implementation, the proposed DeepMorphNet proves to be able to extract features and solve problems that traditional architectures with standard convolution filters cannot. INDEX TERMS Convolutional networks, deep learning, deep morphological networks, mathematical morphology.
doi:10.1109/access.2021.3104405 fatcat:pk5razl7srdy3oybnld3atpjtm

A Triple-Double Convolutional Neural Network for Panchromatic Sharpening [article]

Tian-Jing Zhang, Liang-Jian Deng, Ting-Zhu Huang, Jocelyn Chanussot, Gemine Vivone
2021 arXiv   pre-print
[5] Liang Jian Deng, Gemine Vivone, Cheng Jin, and Jocelyn Chanussot. Detail injection-based deep convolutional neural networks for pansharpening.  ...  Chanussot.  ... 
arXiv:2112.02237v1 fatcat:olcm2ffcffevfdbbjaint4ebvy

Collaborative sliced inverse regression

Alessandro Chiancone, Stéphane Girard, Jocelyn Chanussot
2016 Communications in Statistics - Theory and Methods  
Sliced Inverse Regression (SIR) is an effective method for dimensionality reduction in high-dimensional regression problems. However, the method has requirements on the distribution of the predictors that are hard to check since they depend on unobserved variables. It has been shown that, if the distribution of the predictors is elliptical, then these requirements are satisfied. In case of mixture models, the ellipticity is violated and in addition there is no assurance of a single underlying
more » ... single underlying regression model among the different components. Our approach clusterizes the predictors space to force the condition to hold on each cluster and includes a merging technique to look for different underlying models in the data. A study on simulated data as well as two real applications are provided. It appears that SIR, unsurprisingly, is not capable of dealing with a mixture of Gaussians involving different underlying models whereas our approach is able to correctly investigate the mixture.
doi:10.1080/03610926.2015.1116578 fatcat:gwbpk7xyjvbixj3hvmdon267ny

Geometric Multimodal Deep Learning with Multi-Scaled Graph Wavelet Convolutional Network [article]

Maysam Behmanesh, Peyman Adibi, Mohammad Saeed Ehsani, Jocelyn Chanussot
2021 arXiv   pre-print
Chanussot is with University of Grenoble Alpes, CNRS, Grenoble INP, GIPSA-lab, 38000 Grenoble, France e-mail( Manuscript received December -, 2021; revised -  ...  Mohammad Saeed Ehsani are with Artificial Intelligence Department, Faculty of Computer Engineering, University of Isfahan, Iran e-mail: (,, Jocelyn  ... 
arXiv:2111.13361v1 fatcat:6dluczwatfdcrn6lkvfwauty3m

Spectral Variability Aware Blind Hyperspectral Image Unmixing Based on Convex Geometry [article]

Lucas Drumetz, Jocelyn Chanussot, Christian Jutten, Wing-Kin Ma, Akira Iwasaki
2019 arXiv   pre-print
Hyperspectral image unmixing has proven to be a useful technique to interpret hyperspectral data, and is a prolific research topic in the community. Most of the approaches used to perform linear unmixing are based on convex geometry concepts, because of the strong geometrical structure of the linear mixing model. However, two main phenomena lead to question this model, namely nonlinearities and the spectral variability of the materials. Many algorithms based on convex geometry are still used
more » ... y are still used when considering these two limitations of the linear model. A natural question is to wonder to what extent these concepts and tools (Intrinsic Dimensionality estimation, endmember extraction algorithms, pixel purity) can be safely used in these different scenarios. In this paper, we analyze them with a focus on endmember variability, assuming that the linear model holds. In the light of this analysis, we propose an integrated unmixing chain which tries to adress the shortcomings of the classical tools used in the linear case, based on our previously proposed extended linear mixing model. We show the interest of the proposed approach on simulated and real datasets.
arXiv:1904.03888v1 fatcat:5z37qadx5rbnxfnoxfriwbieqm

An Introduction to Deep Morphological Networks [article]

Keiller Nogueira and Jocelyn Chanussot and Mauro Dalla Mura and Jefersson A. dos Santos
2021 arXiv   pre-print
The recent impressive results of deep learning-based methods on computer vision applications brought fresh air to the research and industrial community. This success is mainly due to the process that allows those methods to learn data-driven features, generally based upon linear operations. However, in some scenarios, such operations do not have a good performance because of their inherited process that blurs edges, losing notions of corners, borders, and geometry of objects. Overcoming this,
more » ... Overcoming this, non-linear operations, such as morphological ones, may preserve such properties of the objects, being preferable and even state-of-the-art in some applications. Encouraged by this, in this work, we propose a novel network, called Deep Morphological Network (DeepMorphNet), capable of doing non-linear morphological operations while performing the feature learning process by optimizing the structuring elements. The DeepMorphNets can be trained and optimized end-to-end using traditional existing techniques commonly employed in the training of deep learning approaches. A systematic evaluation of the proposed algorithm is conducted using two synthetic and two traditional image classification datasets. Results show that the proposed DeepMorphNets is a promising technique that can learn distinct features when compared to the ones learned by current deep learning methods.
arXiv:1906.01751v2 fatcat:feodzexqtbhmpayxrskgwsygim

Pan-sharpening using induction

Muhammad Murtaza Khan, Jocelyn Chanussot, Annick Montanvert, Laurent Condat
2007 2007 IEEE International Geoscience and Remote Sensing Symposium  
Pan-sharpening is the process of improving spatial resolution of multi-spectral (MS) satellite images using the spatial details of a high resolution Panchromatic (PAN) image. Pansharpening can be divided into scaling and fusion processes. In the first part of this paper we use Induction instead of bicubic interpolation for up-scaling the MS images. SFIM (Smoothing Filter based Intensity Modulation) is used to obtain fused MS images for the two different scaling techniques. In the second part,
more » ... the second part, "Indusion", a new fusion technique, derived from Induction, is proposed. In this technique the high frequency content of the PAN image is extracted using a pair of up-scaling and downscaling filters. It is then added to the up-scaled MS images. Finally a comparison of Indusion with Intensity, Hue, Saturation (IHS), Discrete Wavelet Transform (DWT) and SFIM fusion techniques is presented for IKONOS satellite images.
doi:10.1109/igarss.2007.4422793 dblp:conf/igarss/KhanCMC07 fatcat:wjlndsiauzg53aqszcfhvp3oq4

Toward Super-Resolution Image Construction Based on Joint Tensor Decomposition

Xiaoxu Ren, Liangfu Lu, Jocelyn Chanussot
2020 Remote Sensing  
In recent years, fusing hyperspectral images (HSIs) and multispectral images (MSIs) to acquire super-resolution images (SRIs) has been in the spotlight and gained tremendous attention. However, some current methods, such as those based on low rank matrix decomposition, also have a fair share of challenges. These algorithms carry out the matrixing process for the original image tensor, which will lose the structure information of the original image. In addition, there is no corresponding theory
more » ... rresponding theory to prove whether the algorithm can guarantee the accurate restoration of the fused image due to the non-uniqueness of matrix decomposition. Moreover, degenerate operators are usually unknown or difficult to estimate in some practical applications. In this paper, an image fusion method based on joint tensor decomposition (JTF) is proposed, which is more effective and more applicable to the circumstance that degenerate operators are unknown or tough to gauge. Specifically, in the proposed JTF method, we consider SRI as a three-dimensional tensor and redefine the fusion problem with the decomposition issue of joint tensors. We then formulate the JTF algorithm, and the experimental results certify the superior performance of the proposed method in comparison to the current popular schemes.
doi:10.3390/rs12162535 fatcat:u2253qpzszcbpa7mz25y6mlgmm

QNR Optimization based Pansharpening

Muhammad Murtaza Khan, Luciano Alparone, Jocelyn Chanussot
2008 IGARSS 2008 - 2008 IEEE International Geoscience and Remote Sensing Symposium  
Quality Without Reference (QNR) index can be used to globally assess the quality of pansharpened images without the need of a reference high resolution multispectral (MS) image. The QNR index relies on local calculation of the Q4 index. Exploiting the local Q4 calculation property of the QNR index, we propose an injection model for pansharpening. The injection model determines the weight of extracted panchromatic (Pan) details that are to be added into the upscaled MS images to obtain the best
more » ... to obtain the best QNR index. The QNR index calculates spectral distortion of the fused images with respect to the low resolution MS images and spatial distortion of the fused images with respect to the high resolution Pan image. Hence, the QNR optimized fused image is spectrally consistent with the low resolution MS image and spatially consistent with the high resolution Pan image.
doi:10.1109/igarss.2008.4780030 dblp:conf/igarss/KhanAC08a fatcat:rtfophf6ozc57p3zsrz5hdq2e4

Hyperspectral image superresolution: An edge-preserving convex formulation [article]

Miguel Simões, José Bioucas-Dias, Luis B. Almeida, Jocelyn Chanussot
2014 arXiv   pre-print
Hyperspectral remote sensing images (HSIs) are characterized by having a low spatial resolution and a high spectral resolution, whereas multispectral images (MSIs) are characterized by low spectral and high spatial resolutions. These complementary characteristics have stimulated active research in the inference of images with high spatial and spectral resolutions from HSI-MSI pairs. In this paper, we formulate this data fusion problem as the minimization of a convex objective function
more » ... function containing two data-fitting terms and an edge-preserving regularizer. The data-fitting terms are quadratic and account for blur, different spatial resolutions, and additive noise; the regularizer, a form of vector Total Variation, promotes aligned discontinuities across the reconstructed hyperspectral bands. The optimization described above is rather hard, owing to its non-diagonalizable linear operators, to the non-quadratic and non-smooth nature of the regularizer, and to the very large size of the image to be inferred. We tackle these difficulties by tailoring the Split Augmented Lagrangian Shrinkage Algorithm (SALSA)---an instance of the Alternating Direction Method of Multipliers (ADMM)---to this optimization problem. By using a convenient variable splitting and by exploiting the fact that HSIs generally "live" in a low-dimensional subspace, we obtain an effective algorithm that yields state-of-the-art results, as illustrated by experiments.
arXiv:1403.8098v2 fatcat:zpfnkevfmjbjpaqktttsmwrsmm

Special Issue on Machine Learning for Signal Processing

Jocelyn Chanussot, Christian Jutten
2011 Journal of Signal Processing Systems  
doi:10.1007/s11265-011-0627-5 fatcat:uvh5qa5q6fcdlmqgesinq3xj2a

Object recognition in hyperspectral images using Binary Partition Tree representation

Silvia Valero, Philippe Salembier, Jocelyn Chanussot
2015 Pattern Recognition Letters  
., 2010) remote sensing ime-mail: (Silvia Valero), (Philippe Salembier), (Jocelyn Chanussot) ages.  ... 
doi:10.1016/j.patrec.2015.01.003 fatcat:rhq2jzqzdjcjzfcis6fxuuoqqi

Challenges And Opportunities Of Multimodality And Data Fusion In Remote Sensing

Jocelyn Chanussot, Mauro Dalla Mura, P. Gamba, Fabio Pacifici, Saurabh Prasad
2014 Zenodo  
Publication in the conference proceedings of EUSIPCO, Lisbon, Portugal, 2014
doi:10.5281/zenodo.43976 fatcat:pgdxkmjoxzbojnlzznlk57ynga
« Previous Showing results 1 — 15 out of 255 results