• Home
  • Search
  • DO WE STILL NEED IMAGENET PRE-TRAINING IN REMOTE SENSING SCENE CLASSIFICATION?
  • Cite Icon13
  • https://doi.org/10.5194/isprs-archives-xliii-b3-2022-1399-2022Copy DOI Icon

DO WE STILL NEED IMAGENET PRE-TRAINING IN REMOTE SENSING SCENE CLASSIFICATION?

  • Abstract
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Abstract. Due to the scarcity of labeled data, using supervised models pre-trained on ImageNet is a de facto standard in remote sensing scene classification. Recently, the availability of larger high resolution remote sensing (HRRS) image datasets and progress in self-supervised learning have brought up the questions of whether supervised ImageNet pre-training is still necessary for remote sensing scene classification and would supervised pre-training on HRRS image datasets or self-supervised pre-training on ImageNet achieve better results on target remote sensing scene classification tasks. To answer these questions, in this paper we both train models from scratch and fine-tune supervised and self-supervised ImageNet models on several HRRS image datasets. We also evaluate the transferability of learned representations to HRRS scene classification tasks and show that self-supervised pre-training outperforms the supervised one, while the performance of HRRS pre-training is similar to self-supervised pre-training or slightly lower. Finally, we propose using an ImageNet pre-trained model combined with a second round of pre-training using in-domain HRRS images, i.e. domain-adaptive pre-training. The experimental results show that domain-adaptive pre-training results in models that achieve state-of-the-art results on HRRS scene classification benchmarks. The source code and pre-trained models are available at https://github.com/risojevicv/RSSC-transfer.

Loading PDF

Similar Papers
  • Research Article
  • Citations74

SAGN: Semantic-Aware Graph Network for Remote Sensing Scene Classification.

  • Jan 01, 2023
  • IEEE Transactions on Image Processing
  • Yuqun Yang +4
  • Conference Article
  • Citations6

Remote Scene Image Scene Classification Based on Adaptive Segmentation and Dynamic Graph Convolution

  • Jul 11, 2021
  • Yuqun Yang +5
  • PDF
  • Research Article
  • Citations18

A NOVEL FRAMEWORK FOR REMOTE SENSING IMAGE SCENE CLASSIFICATION

  • Apr 30, 2018
  • The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
  • S Jiang +3
  • Research Article
  • Citations222

A semi-supervised generative framework with deep learning features for high-resolution remote sensing image scene classification

  • Nov 14, 2017
  • ISPRS Journal of Photogrammetry and Remote Sensing
  • Wei Han +3
  • Conference Article
  • Citations2

Deep Differential Coding for High-Resolution Remote Sensing Scene Classification

  • Feb 24, 2018
  • Qiuping Shi +3
  • Research Article
  • Citations11

Remote Sensing Scene Classification Using a Preclassification Strategy and an Improved Structural Feature

  • Sep 01, 2017
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • Li-Xin Yuan +2
  • PDF
  • Research Article
  • Citations6

Dual Modality Collaborative Learning for Cross-Source Remote Sensing Retrieval

  • Mar 09, 2022
  • Remote Sensing
  • Jingjing Ma +4
  • Conference Article
  • Citations3

A methodology for Automatic Detection and Extraction of Road Edges from High Resolution Remote Sensing Images

  • Jan 01, 2006
  • Cao Jinxin +2
  • Research Article
  • Citations17

An Improved Pretraining Strategy-Based Scene Classification With Deep Learning

  • Sep 05, 2019
  • IEEE Geoscience and Remote Sensing Letters
  • Zongli Chen +4
  • Research Article
  • Citations3

Remote sensing scene classification based on contextual attention mechanism of lie group space

  • Oct 03, 2024
  • International Journal of Remote Sensing
  • Chengjun Xu +3
  • Research Article
  • Citations42

Meta-Hashing for Remote Sensing Image Retrieval

  • Jan 01, 2022
  • IEEE Transactions on Geoscience and Remote Sensing
  • Xu Tang +7
  • Conference Article
  • Citations4

Multi-Scale Meta-Learning-Based Networks for High-Resolution Remote Sensing Scene Classification

  • Jul 11, 2021
  • Xu Tang +6
  • PDF
  • Research Article
  • Citations28

Fast Binary Coding for the Scene Classification of High-Resolution Remote Sensing Imagery

  • Jun 30, 2016
  • Remote Sensing
  • Fan Hu +4
  • Components

Supp1-3136159.pdf

  • Dec 17, 2021
  • Xu Tang
  • PDF
  • Research Article
  • Citations336

Pre-Trained AlexNet Architecture with Pyramid Pooling and Supervision for High Spatial Resolution Remote Sensing Image Scene Classification

  • Aug 16, 2017
  • Remote Sensing
  • Xiaobing Han +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.