Evaluation of second-order visual features for land-use classification

Negrel, Romain; Picard, David; Gosselin, Philippe-Henri

doi:10.1109/cbmi.2014.6849835

Cited by 70 publications

(34 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2010 SPM [1] 74.00 2010 SPCK++ [1] 76.05 2015 Saliency-UFL [2] 82.72±1.18 2014 Bag-of-SIFT [3] 85.37±1.56 Single-view deep learning 88.00±2.88 2014 SAL-LDA [5] 88.33 2015 Pyramid of spatial relatons [6] 89.1 2014 UFL [3] 90.26±1.51 Multiview deep learning 93.48±0.82 2014 VLAT [7] 94.3…”

Section: Date Methodsmentioning

confidence: 99%

“…The highest accuracies for the UC Merced dataset have been achieved with unsupervised feature learning (UFL) [3] and the vector of locally aggregated tensors (VLAT) method [7], which is an extension of visual dictionary approaches like bag-of-words. Single-view DCNN is outperformed by these methods, but the 90.26% accuracy of UFL can be improved upon with a multiview DCNN which achieves 93.48%.…”

Section: Accuracy Comparisonmentioning

confidence: 99%

“…The UC Merced dataset has been used as a benchmark for land-use classifier evaluation in numerous publications [1]- [7].…”

Section: Datasetmentioning

confidence: 99%

“…The objective of this research was to design a deep convolutional neural network (DCNN) for the UC Merced land-use dataset [1], a dataset compiled in 2010 and used as a benchmark in several land-use classification studies [1]- [7]. The challenge is to optimize classification accuracy by finding a proper selection of DCNN hyper-parameters, which are defined as the DCNN settings, such as the architecture design, convolutional filter bank specifications, pooling layer specifications, and learning rate and momentum values, excluding the learned neuron weights and biases.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Multiview Deep Learning for Land-Use Classification

Luus

Salmon

Bergh

et al. 2015

IEEE Geosci. Remote Sensing Lett.

236

View full text Add to dashboard Cite

Abstract-A multiscale input strategy for multiview deep learning is proposed for supervised multispectral land-use classification and it is validated on a well-known dataset. The hypothesis that simultaneous multiscale views can improve compositionbased inference of classes containing size-varying objects compared to single-scale multiview is investigated. The end-to-end learning system learns a hierarchical feature representation with the aid of convolutional layers to shift the burden of feature determination from hand-engineering to a deep convolutional neural network. This allows the classifier to obtain problemspecific features that are optimal for minimizing the multinomial logistic regression objective, as opposed to user-defined features which trades optimality for generality. A heuristic approach to the optimization of the deep convolutional neural network hyperparameters is used, based on empirical performance evidence. It is shown that a single deep convolutional neural network can be trained simultaneously with multiscale views to improve prediction accuracy over multiple single-scale views. Competitive performance is achieved for the UC Merced dataset where the 93.48% accuracy of multiview deep learning outperforms the 85.37% accuracy of SIFT-based methods and the 90.26% accuracy of unsupervised feature learning.Index Terms-Neural network applications, neural network architecture, feature extraction, urban areas, remote sensing.

show abstract

Section: Date Methodsmentioning

confidence: 99%

Section: Accuracy Comparisonmentioning

confidence: 99%

“…The UC Merced dataset has been used as a benchmark for land-use classifier evaluation in numerous publications [1]- [7].…”

Section: Datasetmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Multiview Deep Learning for Land-Use Classification

Luus

Salmon

Bergh

et al. 2015

IEEE Geosci. Remote Sensing Lett.

236

View full text Add to dashboard Cite

show abstract

“…The current state-of-the-art for this dataset is 94.3% (Negrel et al, 2014) acquired by aggregating tensor products of local descriptors.…”

Section: Datasetsmentioning

confidence: 99%

A Fully Automated Pipeline for Classification Tasks With an Application to Remote Sensing

Suzuki¹,

Claesen²,

Takeda³

et al. 2016

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:Nowadays deep learning has been intensively in spotlight owing to its great victories at major competitions, which undeservedly pushed 'shallow' machine learning methods, relatively naive/handy algorithms commonly used by industrial engineers, to the background in spite of their facilities such as small requisite amount of time/dataset for training. We, with a practical point of view, utilized shallow learning algorithms to construct a learning pipeline such that operators can utilize machine learning without any special knowledge, expensive computation environment, and a large amount of labelled data. The proposed pipeline automates a whole classification process, namely feature-selection, weighting features and the selection of the most suitable classifier with optimized hyperparameters. The configuration facilitates particle swarm optimization, one of well-known metaheuristic algorithms for the sake of generally fast and fine optimization, which enables us not only to optimize (hyper)parameters but also to determine appropriate features/classifier to the problem, which has conventionally been a priori based on domain knowledge and remained untouched or dealt with naïve algorithms such as grid search. Through experiments with the MNIST and CIFAR-10 datasets, common datasets in computer vision field for character recognition and object recognition problems respectively, our automated learning approach provides high performance considering its simple setting (i.e. non-specialized setting depending on dataset), small amount of training data, and practical learning time. Moreover, compared to deep learning the performance stays robust without almost any modification even with a remote sensing object recognition problem, which in turn indicates that there is a high possibility that our approach contributes to general classification problems.

show abstract

Remote Sensing Signature Classification of Agriculture Detection Using Deep Convolution Network Models

Rohith

Kumar

2020

Communications in Computer and Information Science

View full text Add to dashboard Cite

Evaluation of second-order visual features for land-use classification

Cited by 70 publications

References 19 publications

Multiview Deep Learning for Land-Use Classification

Multiview Deep Learning for Land-Use Classification

A Fully Automated Pipeline for Classification Tasks With an Application to Remote Sensing

Remote Sensing Signature Classification of Agriculture Detection Using Deep Convolution Network Models

Contact Info

Product

Resources

About