Deep Feature Fusion for VHR Remote Sensing Scene Classification

By Souleyman Chaib, Huan Liu, Yanfeng Gu, Hongxun Yao. IEEE Transactions on Geoscience and Remote Sensing, 2017

419 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/ed537ab4e0d50f4828ce6351dbb0722d7e5c5d3a

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. Xiwen Yao
4. Guisong Xia
5. Lei Guo
6. Leyuan Fang
7. Peicheng Zhou
8. Shutao Li

In Media Technology

1. Gong Cheng
2. Junwei Han
3. Leyuan Fang
4. Shutao Li
5. Guisong Xia
6. Xiwen Yao
7. Lei Guo
8. Jocelyn Chanussot

Citations in the corpus

• When Deep Learning Meets Metric Learning: Remote Sensing Image Scene Classification via Learning Discriminative CNNs (2018, methodology): “In more recent years, thanks to the availability of largescale training data and the advance of high-performance computing units [51], [52], deep feature learning-based methods [7]–[12], [37]–[42] have been attracting more research attention.”
• Scene Classification With Recurrent Attention of VHR Remote Sensing Images (2019, methodology): “Fusion by addition [25] is the most effective method for remote sensing scene classification, and the proposed ARCNetVGG16 can make an increase of 1.”
• Hyperspectral Image Classification With Deep Feature Fusion Network (2018, background): “[54] effectively fuse the deep features extracted from the first and second fully connected layers for the very high-resolution remote sensing scene classification.”
• Remote Sensing Image Scene Classification Using CNN-CapsNet (2019, methodology): “As for CNN, two representative CNN models (VGG‐16 and Inception‐V3) fully trained on the ImageNet dataset are used as initial feature map extractors, considering their popularity in the remote sensing field [25,27,28,35,53,56,59].”
• CAD-Net: A Context-Aware Detection Network for Objects in Remote Sensing Imagery (2019, background): “And [46] further combines multi-level features for remote sensing scene classification.”
• Continual Contrastive Learning for Cross-Dataset Scene Classification (2022, background): “[29] combined features from each layer of the pre-trained model to construct robust features.”
• Rotation-Insensitive and Context-Augmented Object Detection in Remote Sensing Images (2018, background): “…as scale invariant feature transform [33], histogram of oriented gradients (HOG) [34], and local binary patterns [35], [36], and there are also some frameworks that try to improve image resolution or combine/fuse several features to improve image representation discrimination abilities [37]–[40].”
• Remote Sensing Image Scene Classification Meets Deep Learning: Challenges, Methods, Benchmarks, and Opportunities (2020, methodology): “Fusing multiple features [109], [117], designing effective cost functions [72], [115], modifying deep learning models [72], [118], and data augmentation [84] are all”