Active-Learning-Incorporated Deep Transfer Learning for Hyperspectral Image Classification

A hyperspectral image (HSI) includes a vast quantity of samples, a large number of bands, and randomly occurring redundancy. Classifying such complex data is challenging, and its classification performance can be affected significantly by the amount of labeled training samples, as well as the quality, position, and others factors of these samples. Collecting such labeled training samples is labor and time consuming, motivating the idea of taking advantage of labeled samples from other pre-existing related images. Therefore, transfer learning, which can mitigate the semantic gap between existing and new HSIs, has drawn increasing research attention. However, existing transfer learning methods for HSIs (which mainly concentrate on how to overcome the divergence among images) may fail to carefully consider the contents to be transferred and thus limit their performances. In this paper, we present two novel ideas: 1) we, for the first time, introduce an active learning process to initialize the salient samples on the HSI data, which would be transferred later; and 2) we propose constructing and connecting higher level features for the source and target HSI data to further overcome the cross-domain disparity. Different from existing methods, the proposed framework requires no a priori knowledge on the target domain, and it works for both homogeneous and heterogeneous HSI data. Experimental results on three real-world HSIs support the effectiveness of the proposed method for HSI classification.

[1]  Peng Liu,et al.  Ieee Journal of Selected Topics in Applied Earth Observations and Remote Sensing 1 Active Deep Learning for Classification of Hyperspectral Images , 2022 .

[2]  Andrew McCallum,et al.  Toward Optimal Active Learning through Sampling Estimation of Error Reduction , 2001, ICML.

[3]  Ivor W. Tsang,et al.  Combating Negative Transfer From Predictive Distribution Differences , 2013, IEEE Transactions on Cybernetics.

[4]  Z. Jane Wang,et al.  DT-LET: Deep Transfer Learning by Exploring where to Transfer , 2018, Neurocomputing.

[5]  David D. Lewis,et al.  Heterogeneous Uncertainty Sampling for Supervised Learning , 1994, ICML.

[6]  Mikhail F. Kanevski,et al.  SVM-Based Boosting of Active Learning Strategies for Efficient Domain Adaptation , 2012, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[7]  Shlomo Argamon,et al.  Committee-Based Sampling For Training Probabilistic Classi(cid:12)ers , 1995 .

[8]  H. Sebastian Seung,et al.  Query by committee , 1992, COLT '92.

[9]  Sethuraman Panchanathan,et al.  Batch mode active sampling based on marginal probability distribution matching , 2012, TKDD.

[10]  See-Kiong Ng,et al.  Negative Training Data Can be Harmful to Text Classification , 2010, EMNLP.

[11]  Jeff A. Bilmes,et al.  Deep Canonical Correlation Analysis , 2013, ICML.

[12]  Cees Snoek,et al.  Active Transfer Learning with Zero-Shot Priors: Reusing Past Datasets for Future Tasks , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[13]  Rong Jin,et al.  Active Learning by Querying Informative and Representative Examples , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[15]  John Shawe-Taylor,et al.  Canonical Correlation Analysis: An Overview with Application to Learning Methods , 2004, Neural Computation.

[16]  Xue Li,et al.  Iterative Reweighting Heterogeneous Transfer Learning Framework for Supervised Remote Sensing Image Classification , 2017, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[17]  Jun Li,et al.  Improved hyperspectral image classification by active learning using pre-designed mixed pixels , 2016, Pattern Recognit..

[18]  Qiang Yang,et al.  Active Transfer Learning for Cross-System Recommendation , 2013, AAAI.

[19]  Kilian Q. Weinberger,et al.  Marginalized Denoising Autoencoders for Domain Adaptation , 2012, ICML.

[20]  Yu-Chiang Frank Wang,et al.  Heterogeneous Domain Adaptation and Classification by Exploiting the Correlation Subspace , 2014, IEEE Transactions on Image Processing.

[21]  Saurabh Prasad,et al.  Active and Semisupervised Learning With Morphological Component Analysis for Hyperspectral Image Classification , 2017, IEEE Geoscience and Remote Sensing Letters.

[22]  Lorenzo Bruzzone,et al.  A novel active learning strategy for domain adaptation in the classification of remote sensing images , 2011, 2011 IEEE International Geoscience and Remote Sensing Symposium.

[23]  Ming Shao,et al.  Low-Rank Transfer Subspace Learning , 2012, 2012 IEEE 12th International Conference on Data Mining.

[24]  Qian Du,et al.  GETNET: A General End-to-End 2-D CNN Framework for Hyperspectral Image Change Detection , 2019, IEEE Transactions on Geoscience and Remote Sensing.

[25]  Fuzhen Zhuang,et al.  Supervised Representation Learning: Transfer Learning with Deep Autoencoders , 2015, IJCAI.

[26]  Maria-Florina Balcan,et al.  Margin Based Active Learning , 2007, COLT.

[27]  Jinbo Bi,et al.  Active learning via transductive experimental design , 2006, ICML.

[28]  Daphne Koller,et al.  Support Vector Machine Active Learning with Application sto Text Classification , 2000, ICML.

[29]  Qi Wang,et al.  Optimal Clustering Framework for Hyperspectral Band Selection , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[30]  Sean Hughes,et al.  Clustering by Fast Search and Find of Density Peaks , 2016 .

[31]  Yun Fu,et al.  Task-driven deep transfer learning for image classification , 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[32]  Jinhui Tang,et al.  Generalized Deep Transfer Networks for Knowledge Propagation in Heterogeneous Domains , 2016, ACM Trans. Multim. Comput. Commun. Appl..

[33]  Daphne Koller,et al.  Support Vector Machine Active Learning with Applications to Text Classification , 2000, J. Mach. Learn. Res..

[34]  Zhenghang Yuan,et al.  GETNET: A General End-to-end Two-dimensional CNN Framework for Hyperspectral Image Change Detection , 2019, ArXiv.

[35]  Claudio Persello,et al.  Interactive Domain Adaptation for the Classification of Remote Sensing Images Using Active Learning , 2013, IEEE Geoscience and Remote Sensing Letters.

[36]  H. Sebastian Seung,et al.  Selective Sampling Using the Query by Committee Algorithm , 1997, Machine Learning.

[37]  Rama Chellappa,et al.  Visual Domain Adaptation: A survey of recent advances , 2015, IEEE Signal Processing Magazine.

[38]  Yoshua Bengio,et al.  Domain Adaptation for Large-Scale Sentiment Classification: A Deep Learning Approach , 2011, ICML.

[39]  Giles M. Foody,et al.  Toward intelligent training of supervised image classifications: directing training data acquisition for SVM classification , 2004 .

[40]  Bo Du,et al.  A Novel Semisupervised Active-Learning Algorithm for Hyperspectral Image Classification , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[41]  Lorenzo Bruzzone,et al.  Active Learning for Domain Adaptation in the Supervised Classification of Remote Sensing Images , 2012, IEEE Transactions on Geoscience and Remote Sensing.

[42]  Sanjoy Dasgupta,et al.  Hierarchical sampling for active learning , 2008, ICML '08.

[43]  Z. Jane Wang,et al.  Deep Transfer Learning for Hyperspectral Image Classification , 2018, 2018 IEEE 20th International Workshop on Multimedia Signal Processing (MMSP).