# Towards Better Exploiting Convolutional Neural Networks for Remote Sensing Scene Classification

arXiv: https://arxiv.org/abs/1602.01517 · HTML: https://mlsanity.com/paper/1602.01517/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Feb 2016.

## Built on by (most cited first, 29 of 29)

- [Towards Geospatial Foundation Models via Continual Pretraining](https://mlsanity.com/paper/2302.04476/) (2023)
- [STAR: A First-Ever Dataset and A Large-Scale Benchmark for Scene Graph Generation in Large-Size Satellite Imagery](https://mlsanity.com/paper/2406.09410/) (2024)
- [Panoptic Segmentation Meets Remote Sensing](https://mlsanity.com/paper/2111.12126/) (2021)
- [Comparison of fine-tuning strategies for transfer learning in medical image classification](https://mlsanity.com/paper/2406.10050/) (2024)
- [RescueADI: Adaptive Disaster Interpretation in Remote Sensing Images with Autonomous Agents](https://mlsanity.com/paper/2410.13384/) (2024)
- [Deep Learning for Scene Classification: A Survey](https://mlsanity.com/paper/2101.10531/) (2021)
- [Aerial Scene Parsing: From Tile-level Scene Classification to Pixel-wise Semantic Labeling](https://mlsanity.com/paper/2201.01953/) (2022)
- [All Grains, One Scheme (AGOS): Learning Multi-grain Instance Representation for Aerial Scene Classification](https://mlsanity.com/paper/2205.03371/) (2022)
- [Do we still need ImageNet pre-training in remote sensing scene classification?](https://mlsanity.com/paper/2111.03690/) (2021)
- [Self-Supervised In-Domain Representation Learning for Remote Sensing Image Scene Classification](https://mlsanity.com/paper/2302.01793/) (2023)
- [A Robust and Low Complexity Deep Learning Model for Remote Sensing Image Classification](https://mlsanity.com/paper/2211.02820/) (2022)
- [WV-Net: A foundation model for SAR WV-mode satellite imagery trained using contrastive self-supervised learning on 10 million images](https://mlsanity.com/paper/2406.18765/) (2024)
- [Cloud Adversarial Example Generation for Remote Sensing Image Classification](https://mlsanity.com/paper/2409.14240/) (2024)
- [RedBit: An End-to-End Flexible Framework for Evaluating the Accuracy of Quantized CNNs](https://mlsanity.com/paper/2301.06193/) (2023)
- [Human-annotated label noise and their impact on ConvNets for remote sensing image scene classification](https://mlsanity.com/paper/2305.12106/) (2023)
- [On the Adversarial Vulnerabilities of Transfer Learning in Remote Sensing](https://mlsanity.com/paper/2501.11462/) (2025)
- [Learning with less: label-efficient land cover classification at very high spatial resolution using self-supervised deep learning](https://mlsanity.com/paper/2511.03004/) (2025)
- [Global Cross-Modal Geo-Localization: A Million-Scale Dataset and a Physical Consistency Learning Framework](https://mlsanity.com/paper/2603.08491/) (2026)
- [MLMA-Net: multi-level multi-attentional learning for multi-label object detection in textile defect images](https://mlsanity.com/paper/2102.00376/) (2021)
- [A Hierarchical Approach to Remote Sensing Scene Classification](https://mlsanity.com/paper/2103.15463/) (2021)
- [Cloud based Scalable Object Recognition from Video Streams using Orientation Fusion and Convolutional Neural Networks](https://mlsanity.com/paper/2106.15329/) (2021)
- [Window Detection In Facade Imagery: A Deep Learning Approach Using Mask R-CNN](https://mlsanity.com/paper/2107.10006/) (2021)
- [AutoMC: Automated Model Compression based on Domain Knowledge and Progressive search strategy](https://mlsanity.com/paper/2201.09884/) (2022)
- [Feature Transformation for Cross-domain Few-shot Remote Sensing Scene Classification](https://mlsanity.com/paper/2203.02270/) (2022)
- [Supervised and Contrastive Self-Supervised In-Domain Representation Learning for Dense Prediction Problems in Remote Sensing](https://mlsanity.com/paper/2301.12541/) (2023)
- [Multiview Transformer: Rethinking Spatial Information in Hyperspectral Image Classification](https://mlsanity.com/paper/2310.07186/) (2023)
- [Deep Learning Meets OBIA: Tasks, Challenges, Strategies, and Perspectives](https://mlsanity.com/paper/2408.01607/) (2024)
- [Improving the network traffic classification using the Packet Vision approach](https://mlsanity.com/paper/2412.19360/) (2024)
- [Bio-inspired fine-tuning for selective transfer learning in image classification](https://mlsanity.com/paper/2601.11235/) (2026)

## Abstract (arXiv)

We present an analysis of three possible strategies for exploiting the power of existing convolutional neural networks (ConvNets) in different scenarios from the ones they were trained: full training, fine tuning, and using ConvNets as feature extractors. In many applications, especially including remote sensing, it is not feasible to fully design and train a new ConvNet, as this usually requires a considerable amount of labeled data and demands high computational costs. Therefore, it is important to understand how to obtain the best profit from existing ConvNets. We perform experiments with six popular ConvNets using three remote sensing datasets. We also compare ConvNets in each strategy with existing descriptors and with state-of-the-art baselines. Results point that fine tuning tends to be the best performing strategy. In fact, using the features from the fine-tuned ConvNet with linear SVM obtains the best results. We also achieved state-of-the-art results for the three datasets used.