Multi-Task Joint Sparse and Low-Rank Representation for the Scene Classification of High-Resolution Remote Sensing Image

Qi, Kunlun; Liu, Wenxuan; Yang, Chao; Guan, Qingfeng; Wu, Huayi

doi:10.3390/rs9010010

Cited by 26 publications

(21 citation statements)

References 46 publications

(78 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It presents that the MDDC outperforms these previously proposed methods. Our proposed method achieved about 6.53% improvement over the MTJSLRC method [55] which utilized a combination of multiple sets of features. Overall, the remarkable classification results achieved on these public benchmarks indicate the superior discriminative capability of the proposed feature representation for the land-use scene.…”

Section: Comparison With State-of-the-art Methodsmentioning

confidence: 93%

“…BoVW [15] 71.86 SPM [19] 74.0 SPCK++ [4] 77.38 MS-based Correlaton [20] 81.32 ± 0.92 UFL [7] 81.67 ± 1.23 SG + UFL [8] 82.72 ± 1.18 UFL-SC [10] 90.26 ± 1.51 UFC + MSC [11] 91.95 ± 0.72 CCM-BoVW [21] 86.64 ± 0.81 PSR [22] 89.1 MSIFT [6] 90.97 ± 1.81 MS-CLBP + FV [56] 93.0 ± 1.2 MTJSLRC [55] 91.07 ± 0.67 VLAT [57] 94.3 MBVW [25] 96.14 OverFeat [31] 90.91 ± 1.19 CaffeNet [31] 93.42 ± 1.0 GoogLeNet + Fine-tune [53] 97.1…”

Section: Methodsmentioning

confidence: 99%

“…Bag of SIFT [58] 85.5 ± 1.2 LTP-HF [59] 77.6 MS-CLBP [59] 93.4 ± 1.1 Multi-feature Concatenation [58] 90.8 ± 0.7 MTJSLRC [55] 91.74 ± 1.14 SIFT + LTP-HF + Color Histogram [48] 93.6 MS-CLBP + FV [56] 94.32 ± 1.2…”

Section: Methods Accuracy (Mean ± Std)mentioning

confidence: 99%

See 2 more Smart Citations

A Multiscale Deeply Described Correlatons-Based Model for Land-Use Scene Classification

Yang

Guan

et al. 2017

Remote Sensing

Self Cite

View full text Add to dashboard Cite

Abstract:Research efforts in land-use scene classification is growing alongside the popular use of High-Resolution Satellite (HRS) images. The complex background and multiple land-cover classes or objects, however, make the classification tasks difficult and challenging. This article presents a Multiscale Deeply Described Correlatons (MDDC)-based algorithm which incorporates appearance and spatial information jointly at multiple scales for land-use scene classification to tackle these problems. Specifically, we introduce a convolutional neural network to learn and characterize the dense convolutional descriptors at different scales. The resulting multiscale descriptors are used to generate visual words by a general mapping strategy and produce multiscale correlograms of visual words. Then, an adaptive vector quantization of multiscale correlograms, termed multiscale correlatons, are applied to encode the spatial arrangement of visual words at different scales. Experiments with two publicly available land-use scene datasets demonstrate that our MDDC model is discriminative for efficient representation of land-use scene images, and achieves competitive classification results with state-of-the-art methods.

show abstract

Section: Comparison With State-of-the-art Methodsmentioning

confidence: 93%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A Multiscale Deeply Described Correlatons-Based Model for Land-Use Scene Classification

Yang

Guan

et al. 2017

Remote Sensing

Self Cite

View full text Add to dashboard Cite

show abstract

“…BOVW [15] 71.86 SPM [21] 74.0 SPCK++ [4] 77.38 UFL [7] 81.67 ± 1.23 SG+UFL [8] 82.72 ± 1.18 VLAT [62] 94.3 MS-CLBP+FV [61] 93.0 ± 1.2 MTJSLRC [63] 91.07 ± 0.67 MBVW [25] 96.14 CaffeNet [31] 93.42 ± 1.0 OverFeat [31] 90.91 ± 1.19 MDDC [39] 96.92 ± 0.57 GoogLeNet + Fine-tune [59] 97.1 CCP-net 97.52 ± 0.97…”

Section: Methodsmentioning

confidence: 99%

Concentric Circle Pooling in Deep Convolutional Networks for Remote Sensing Scene Classification

Guan

Yang

et al. 2018

Remote Sensing

Self Cite

View full text Add to dashboard Cite

Convolutional neural networks (CNNs) have been increasingly used in remote sensing scene classification/recognition. The conventional CNNs are sensitive to the rotation of the image scene, which will inevitably result in the misclassification of remote sensing scene images that belong to the same category. In this work, we equip the networks with a new pooling strategy, "concentric circle pooling", to alleviate the above problem. The new network structure, called CCP-net can generate a concentric circle-based spatial-rotation-invariant representation of an image, hence improving the classification accuracy. The square kernel is adopted to approximate the circle kernels in concentric circle pooling, which is much more efficient and suitable for CNNs to propagate gradients. We implement the training of the proposed network structure with standard back-propagation, thus CCP-net is an end-to-end trainable CNNs. With these advantages, CCP-net should in general improve CNN-based remote sensing scene classification methods. Experiments using two publicly available remote sensing scene datasets demonstrate that using CCP-net can achieve competitive classification results compared with the state-of-art methods.

show abstract

“…Multi-Task Learning (MTL) is a learning paradigm in machine learning and its purpose is to take advantage of useful information contributed by multiple related tasks to improve the generalization performance of all the tasks [11]. MTL has shown significant advantage to single-task learning because of its ability to facilitate knowledge sharing between tasks [31], e.g., bioinformatics and health informatics [32,33], web applications [34,35] and remote sensing [36][37][38].…”

Section: Multi-task Learning In Human Activity Recognitionmentioning

confidence: 99%

Context-Aware Human Activity and Smartphone Position-Mining with Motion Sensors

et al. 2019

View full text Add to dashboard Cite

Today's smartphones are equipped with embedded sensors, such as accelerometers and gyroscopes, which have enabled a variety of measurements and recognition tasks. In this paper, we jointly investigate two types of recognition problems in a joint manner, e.g., human activity recognition and smartphone on-body position recognition, in order to enable more robust context-aware applications. So far, these two problems have been studied separately without considering the interactions between each other. In this study, by first applying a novel data preprocessing technique, we propose a joint recognition framework based on the multi-task learning strategy, which can reduce computational demand, better exploit complementary information between the two recognition tasks, and lead to higher recognition performance. We also extend the joint recognition framework so that additional information, such as user identification with biometric motion analysis, can be offered. We evaluate our work systematically and comprehensively on two datasets with real-world settings. Our joint recognition model achieves the promising performance of 0.9174 in terms of F1-score for user identification on the benchmark RealWorld Human Activity Recognition (HAR) dataset. On the other hand, in comparison with the conventional approach, the proposed joint model is shown to be able to improve human activity recognition and position recognition by 5.1% and 9.6% respectively.

show abstract

Multi-Task Joint Sparse and Low-Rank Representation for the Scene Classification of High-Resolution Remote Sensing Image

Cited by 26 publications

References 46 publications

A Multiscale Deeply Described Correlatons-Based Model for Land-Use Scene Classification

A Multiscale Deeply Described Correlatons-Based Model for Land-Use Scene Classification

Concentric Circle Pooling in Deep Convolutional Networks for Remote Sensing Scene Classification

Context-Aware Human Activity and Smartphone Position-Mining with Motion Sensors

Contact Info

Product

Resources

About