{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/towards-better-exploiting-convolutional","title":"Towards Better Exploiting Convolutional Neural Networks for Remote Sensing Scene Classification","arxiv_id":"1602.01517","date":"2016-02-04","proceeding":null,"authors":["Keiller Nogueira","Otávio A. B. Penatti","Jefersson A. dos Santos"],"abstract":"We present an analysis of three possible strategies for exploiting the power\nof existing convolutional neural networks (ConvNets) in different scenarios\nfrom the ones they were trained: full training, fine tuning, and using ConvNets\nas feature extractors. In many applications, especially including remote\nsensing, it is not feasible to fully design and train a new ConvNet, as this\nusually requires a considerable amount of labeled data and demands high\ncomputational costs. Therefore, it is important to understand how to obtain the\nbest profit from existing ConvNets. We perform experiments with six popular\nConvNets using three remote sensing datasets. We also compare ConvNets in each\nstrategy with existing descriptors and with state-of-the-art baselines. Results\npoint that fine tuning tends to be the best performing strategy. In fact, using\nthe features from the fine-tuned ConvNet with linear SVM obtains the best\nresults. We also achieved state-of-the-art results for the three datasets used.","url_abs":"http://arxiv.org/abs/1602.01517v1","url_pdf":"http://arxiv.org/pdf/1602.01517v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"towards-better-exploiting-convolutional","repo_url":"https://github.com/keillernogueira/exploit-cnn-rs","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"caffe2","reach":{"status":"ok"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"scene-classification","task_name":"Scene Classification"}],"methods":[{"method_slug":"svm","method_name":"SVM"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1602.01517","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}