Auto-encoder-based shared mid-level visual dictionary learning for scene classification using very high resolution remote sensing images

By Gong Cheng, Peicheng Zhou, Junwei Han, Lei Guo, Jungong Han. 2015

63 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Junwei Han
2. Gong Cheng
3. Peicheng Zhou
4. Xiwen Yao
5. Lei Guo
6. Shuhui Bu
7. Chao Yao
8. Zhenbao Liu

In Media Technology

1. Gong Cheng
2. Junwei Han
3. Peicheng Zhou
4. Xiwen Yao
5. Lei Guo
6. Chao Yao
7. Shuhui Bu
8. Xuelong Li

Citations in the corpus

• Remote Sensing Image Scene Classification Meets Deep Learning: Challenges, Methods, Benchmarks, and Opportunities (2020, unknown): “[93] demonstrated mid-level visual feature learned from autoencoder-based method is discriminative and able to facilitate scene classification tasks.”
• Weakly supervised target detection in remote sensing images based on transferred deep features and negative bootstrapping (2015, background): “…gradient (HoG) Cheng et al. 2013b) or mid-level features (e.g. bag-of-words (BoW) Csurka et al. 2004, locality-constrained linear coding (LLC) Wang et al. 2010, sparsely-constructed Gaussian processes (L1-GPs) Liu et al. 2014, and Sparselets Cheng et al. 2015a,b,c), to describe image patches.”
• A Survey on Object Detection in Optical Remote Sensing Images (2016, unknown): “…methods (Cheng et al., 2013b; Cheng et al., 2014a, b; Zhang et al., 2014b; Zhang et al., 2015b) and the sparelets work (Cheng et al., 2015a; Cheng et al., 2015b; Cheng et al., 2015c) -norm: , -norm: ‹ where x is a small constant and the results are insensitive to the value of x over a…”
• Hyperspectral Image Classification—Traditional to Deep Models: A Survey for Future Prospects (2021, unknown): “remote sensing related works [32], [57], [58].”
• Object detection in VHR optical remote sensing images via learning rotation-invariant HOG feature (2016, background): “More recently, with the advances of machine learning, especially the powerful feature representations and classifiers, many approaches regarded object detection as a classification problem [1-22].”
• When Deep Learning Meets Metric Learning: Remote Sensing Image Scene Classification via Learning Discriminative CNNs (2018, background): “tors [19]–[22] are the most widely used feature representations.”
• Learning Rotation-Invariant Convolutional Neural Networks for Object Detection in VHR Optical Remote Sensing Images (2016, methodology): “Moreover, some part model-based methods and the sparselets work [34]–[36] that built on the HOG feature have also shown”
• Scene classification of high resolution remote sensing images using convolutional neural networks (2016, methodology): “However, most of them are based on handcrafted or shallow learning-based features, such as bag-of-visual-words (BOVW) model [23] and its variations [4, 20, 21], sparse coding-based features [12, 19], midlevel visual elements-oriented features [9, 11, 15, 18] and so on.”
• Scene Classification With Recurrent Attention of VHR Remote Sensing Images (2019, background): “Scale-invariant feature transform (SIFT) [10], [28] and histogram of oriented gradients [29], [30] are local features that usually need mid-level descriptor to generate the entire representation [10], [31].”
• Semantic Classification of High-Resolution Remote-Sensing Images Based on Mid-level Features (2016, background): “[12] introduced the auto-encoder model in deep learning into mid-level vocabulary learning.”