TrAdaBoost Based on Improved Particle Swarm Optimization for Cross-Domain Scene Classification With Limited Samples

Li, Yan; Zhu, Ruixi; Liu, Yi; Mo, Nan

doi:10.1109/jstars.2018.2859836

Cited by 28 publications

(15 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is increasingly significant to use high-resolution remote sensing images (HRRSI) in geospatial object detection [1,2] or land-cover classification tasks due to the advance of remote sensing instruments. As we all know, scene classification (that classifies scene images into diverse categories according to the semantic information they contain), has been widely applied to land-cover or land-use classification of HRRSI [3][4][5][6]. Nevertheless, it is difficult to classify the scene images effectively due to various land-cover objects and high intra-class diversity [7,8].…”

Section: Introductionmentioning

confidence: 99%

RETRACTED: Attention-Based Deep Feature Fusion for the Scene Classification of High-Resolution Remote Sensing Images

Zhu

Yan

et al. 2019

Remote Sensing

View full text Add to dashboard Cite

Scene classification of highresolution remote sensing images (HRRSI) is one of the most important means of landcover classification. Deep learning techniques, especially the convolutional neural network (CNN) have been widely applied to the scene classification of HRRSI due to the advancement of graphic processing units (GPU). However, they tend to extract features from the whole images rather than discriminative regions. The visual attention mechanism can force the CNN to focus on discriminative regions, but it may suffer from the influence of intraclass diversity and repeated texture. Motivated by these problems, we propose an attention-based deep feature fusion (ADFF) framework that constitutes three parts, namely attention maps generated by Gradientweighted Class Activation Mapping (GradCAM), a multiplicative fusion of deep features and the centerbased cross-entropy loss function. First of all, we propose to make attention maps generated by GradCAM as an explicit input in order to force the network to concentrate on discriminative regions. Then, deep features derived from original images and attention maps are proposed to be fused by multiplicative fusion in order to consider both improved abilities to distinguish scenes of repeated texture and the salient regions. Finally, the centerbased cross-entropy loss function that utilizes both the cross-entropy loss and center loss function is proposed to backpropagate fused features so as to reduce the effect of intraclass diversity on feature representations. The proposed ADFF architecture is tested on three benchmark datasets to show its performance in scene classification. The experiments confirm that the proposed method outperforms most competitive scene classification methods with an average overall accuracy of 94% under different training ratios.

show abstract

Section: Introductionmentioning

confidence: 99%

RETRACTED: Attention-Based Deep Feature Fusion for the Scene Classification of High-Resolution Remote Sensing Images

Zhu

Yan

et al. 2019

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…DA has been exploited in the remote sensing community to cope with multi-temporal and multi-source satellite images, where differences in atmospheric illuminations and ground conditions can easily ruin the adaptation of a model (Bruzzone, & Persello, 2009;Volpi et al, 2015;Matasci et al, 2015;Samat et al, 2016;Yan et al, 2018b;Yan et al, 2019;Zhu et al, 2019;Ma et al, 2019). In 2009, Bruzzone & Persello (2009) proposed a feature selection method accomplished by a multi-objective criterion function to improve the discrimination in hyperspectral image classification.…”

Section: Domain Adaptationmentioning

confidence: 99%

Cross-regional oil palm tree counting and detection via a multi-level attention domain adaptation network

Zheng

et al. 2020

ISPRS Journal of Photogrammetry and Remote Sensing

View full text Add to dashboard Cite

“…Jiang et al [47] raised a method to remove miss-leading training examples from the source domain based on the difference between the conditional probabilities P(yT | xT) and P(yS | xS). TrAdaBoost has been widely applied in different domains [48][49] [50], and exhibit better performance in cross-domain image classification. A lot of pedestrian retrieval research also introduces transfer learning methods.…”

Section: Transfer Learningmentioning

confidence: 99%

“…This effectively expands the volume of data for model training. In recent researches, TrAdaBoost is proved to have good performance on image filtering [48][49] [50]. Before applying TrAdaBoost, it was necessary to adapt the algorithm, as described in Algorithm 1.…”

Section: Tradaboost Based Transfer Learningmentioning

confidence: 99%

FSRM-STS: Cross-dataset pedestrian retrieval based on a four-stage retrieval model with Selection–Translation–Selection

Huang

et al. 2020

Future Generation Computer Systems

View full text Add to dashboard Cite

Pedestrian retrieval is widely used in intelligent video surveillance and is closely related to people's lives. Although pedestrian retrieval from a single dataset has improved in recent years, obstacles such as a lack of sample data, domain gaps within and between datasets (arising from factors such as variation in lighting conditions, resolution, season and background etc), reduce the generalizability of existing models. Factors such as these can act as barriers to the practical use of this technology. Cross-dataset learning is a way to obtain high-quality images from source datasets and can assist the learning of target datasets, thus helping to address the above problem. Existing studies of cross-dataset learning directly apply translated images from source datasets to target datasets, and seldom consider systematic strategies for further improving the quality of the translated images. There is therefore room for improvement in cross-dataset learning. This paper proposes a four-stage retrieval model based on Selection-Translation-Selection (FSRM-STS), to help address this problem. In the first stage of the model, images in pedestrian retrieval datasets are semantically segmented to provide information for image-translation. In the second stage, STS is proposed, based on four strategies to obtain high quality translation results from all source datasets and to generate auxiliary datasets. In the third stage, a pedestrian feature extraction model is proposed, based on both the auxiliary and target datasets. This converts each image in target datasets into an n-dimensional vector. In the final stage, the extracted image vectors are used for cross-dataset pedestrian retrieval. As the translation quality is improved, FSRM-STS achieves promising results for the cross-dataset pedestrian retrieval. Experimental results on four benchmark datasets Market-1501, DukeMTMC-reID, CUHK03 and VIPeR show the effectiveness of the proposed model. Finally, the use of parallel computing for accelerating the training speed and for realizing online applications is also discussed. A primary demo based on cloud computing is designed to verify the engineering solution in the future.

show abstract

TrAdaBoost Based on Improved Particle Swarm Optimization for Cross-Domain Scene Classification With Limited Samples

Cited by 28 publications

References 49 publications

RETRACTED: Attention-Based Deep Feature Fusion for the Scene Classification of High-Resolution Remote Sensing Images

RETRACTED: Attention-Based Deep Feature Fusion for the Scene Classification of High-Resolution Remote Sensing Images

Cross-regional oil palm tree counting and detection via a multi-level attention domain adaptation network

FSRM-STS: Cross-dataset pedestrian retrieval based on a four-stage retrieval model with Selection–Translation–Selection

Contact Info

Product

Resources

About