Improving Deep Forest via Patch-Based Pooling, Morphological Profiling, and Pseudo Labeling for Remote Sensing Image Classification
Deep forest (DF), an alternative to neural networks (NNs)-based deep learning (DL), has gained increasing attentions in recent years. Despite its remarkable advantages, the original multigrained cascade forest (gcForest) is limited by the high time cost and memory requirement. To overcome this limit...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9531400/ |
| _version_ | 1798022370441560064 |
|---|---|
| author | Alim Samat Erzhu Li Peijun Du Sicong Liu Zelang Miao |
| author_facet | Alim Samat Erzhu Li Peijun Du Sicong Liu Zelang Miao |
| author_sort | Alim Samat |
| collection | DOAJ |
| description | Deep forest (DF), an alternative to neural networks (NNs)-based deep learning (DL), has gained increasing attentions in recent years. Despite its remarkable advantages, the original multigrained cascade forest (gcForest) is limited by the high time cost and memory requirement. To overcome this limitation, gcForest with confidence screening (gcForestCS) and feature screening (gcForestFS) were proposed with the proven improvements. But they were not comparatively studied for remote sensing (RS) image classification. Furthermore, gcForest, gcForestCS, and gcForestFS could be further improved by introducing patch-based pooling (PP), morphological profiling (MP), and pseudo labeling (PL) techniques. In this sense, DF algorithms are introduced and comparatively studied for hyperspectral and polarimetric synthetic aperture radar (PolSAR) image classification first. To further foster the classification performance from accurate, efficient, and effective feature abstraction viewpoints, improved versions of gcForest, gcForestCS, and gcForestFS, are proposed by adopting PP, MP, and PL techniques. To evaluate the performance of the introduced and proposed DF algorithms, six state-of-the-art spectral-spatial features aware NNs based DL algorithms are selected. Experimental results on three widely acknowledged hyperspectral and PolSAR benchmarks showed that: 1) gcForest, gcForestCS, and gcForestFS are also advanced algorithms for RS image classification; 2) mixed pooling with larger patch size set is always the best option in contrast with average, maximum, minimum, and median pooling strategies; and 3) positive improvements on gcForest, gcForestCS, and gcForestFS are clear using PP, MP, and PL techniques, and the best improvements can always be obtained by fused usage of PP and MP with PL features. |
| first_indexed | 2024-04-11T17:28:47Z |
| format | Article |
| id | doaj.art-47a470a216b74801b0ce338f126c0082 |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-04-11T17:28:47Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-47a470a216b74801b0ce338f126c00822022-12-22T04:12:11ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352021-01-01149334934910.1109/JSTARS.2021.31109949531400Improving Deep Forest via Patch-Based Pooling, Morphological Profiling, and Pseudo Labeling for Remote Sensing Image ClassificationAlim Samat0https://orcid.org/0000-0002-9091-6033Erzhu Li1https://orcid.org/0000-0002-5881-618XPeijun Du2Sicong Liu3https://orcid.org/0000-0003-1612-4844Zelang Miao4https://orcid.org/0000-0002-1499-2288State Key Laboratory of Desert and Oasis Ecology, Xinjiang Institute of Ecology and Geography, Chinese Academy of Sciences, Urumqi, Xinjiang, ChinaDepartment of Geographical Information Science, Jiangsu Normal University, Xuzhou, Jiangsu, ChinaSchool of Geography and Ocean Science, Nanjing University, Nanjing, Jiangsu, ChinaCollege of Surveying and Geoinformatics, Tongji University, Shanghai, ChinaSchool of Geosciences and Info-Physics, Central South University, Changsha, Hunan, ChinaDeep forest (DF), an alternative to neural networks (NNs)-based deep learning (DL), has gained increasing attentions in recent years. Despite its remarkable advantages, the original multigrained cascade forest (gcForest) is limited by the high time cost and memory requirement. To overcome this limitation, gcForest with confidence screening (gcForestCS) and feature screening (gcForestFS) were proposed with the proven improvements. But they were not comparatively studied for remote sensing (RS) image classification. Furthermore, gcForest, gcForestCS, and gcForestFS could be further improved by introducing patch-based pooling (PP), morphological profiling (MP), and pseudo labeling (PL) techniques. In this sense, DF algorithms are introduced and comparatively studied for hyperspectral and polarimetric synthetic aperture radar (PolSAR) image classification first. To further foster the classification performance from accurate, efficient, and effective feature abstraction viewpoints, improved versions of gcForest, gcForestCS, and gcForestFS, are proposed by adopting PP, MP, and PL techniques. To evaluate the performance of the introduced and proposed DF algorithms, six state-of-the-art spectral-spatial features aware NNs based DL algorithms are selected. Experimental results on three widely acknowledged hyperspectral and PolSAR benchmarks showed that: 1) gcForest, gcForestCS, and gcForestFS are also advanced algorithms for RS image classification; 2) mixed pooling with larger patch size set is always the best option in contrast with average, maximum, minimum, and median pooling strategies; and 3) positive improvements on gcForest, gcForestCS, and gcForestFS are clear using PP, MP, and PL techniques, and the best improvements can always be obtained by fused usage of PP and MP with PL features.https://ieeexplore.ieee.org/document/9531400/Deep forest (DF)deep learning (DL)ensemble learning (EL)image classificationmultigrained cascade forest (gcForest) |
| spellingShingle | Alim Samat Erzhu Li Peijun Du Sicong Liu Zelang Miao Improving Deep Forest via Patch-Based Pooling, Morphological Profiling, and Pseudo Labeling for Remote Sensing Image Classification IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Deep forest (DF) deep learning (DL) ensemble learning (EL) image classification multigrained cascade forest (gcForest) |
| title | Improving Deep Forest via Patch-Based Pooling, Morphological Profiling, and Pseudo Labeling for Remote Sensing Image Classification |
| title_full | Improving Deep Forest via Patch-Based Pooling, Morphological Profiling, and Pseudo Labeling for Remote Sensing Image Classification |
| title_fullStr | Improving Deep Forest via Patch-Based Pooling, Morphological Profiling, and Pseudo Labeling for Remote Sensing Image Classification |
| title_full_unstemmed | Improving Deep Forest via Patch-Based Pooling, Morphological Profiling, and Pseudo Labeling for Remote Sensing Image Classification |
| title_short | Improving Deep Forest via Patch-Based Pooling, Morphological Profiling, and Pseudo Labeling for Remote Sensing Image Classification |
| title_sort | improving deep forest via patch based pooling morphological profiling and pseudo labeling for remote sensing image classification |
| topic | Deep forest (DF) deep learning (DL) ensemble learning (EL) image classification multigrained cascade forest (gcForest) |
| url | https://ieeexplore.ieee.org/document/9531400/ |
| work_keys_str_mv | AT alimsamat improvingdeepforestviapatchbasedpoolingmorphologicalprofilingandpseudolabelingforremotesensingimageclassification AT erzhuli improvingdeepforestviapatchbasedpoolingmorphologicalprofilingandpseudolabelingforremotesensingimageclassification AT peijundu improvingdeepforestviapatchbasedpoolingmorphologicalprofilingandpseudolabelingforremotesensingimageclassification AT sicongliu improvingdeepforestviapatchbasedpoolingmorphologicalprofilingandpseudolabelingforremotesensingimageclassification AT zelangmiao improvingdeepforestviapatchbasedpoolingmorphologicalprofilingandpseudolabelingforremotesensingimageclassification |