{"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/selective-unsupervised-feature-learning-with","title":"Selective Unsupervised Feature Learning with Convolutional Neural Network (S-CNN)","arxiv_id":"1606.02210","date":"2016-06-07","proceeding":null,"authors":["Amir Ghaderi","Vassilis Athitsos"],"abstract":"Supervised learning of convolutional neural networks (CNNs) can require very\nlarge amounts of labeled data. Labeling thousands or millions of training\nexamples can be extremely time consuming and costly. One direction towards\naddressing this problem is to create features from unlabeled data. In this\npaper we propose a new method for training a CNN, with no need for labeled\ninstances. This method for unsupervised feature learning is then successfully\napplied to a challenging object recognition task. The proposed algorithm is\nrelatively simple, but attains accuracy comparable to that of more\nsophisticated methods. The proposed method is significantly easier to train,\ncompared to existing CNN methods, making fewer requirements on manually labeled\ntraining data. It is also shown to be resistant to overfitting. We provide\nresults on some well-known datasets, namely STL-10, CIFAR-10, and CIFAR-100.\nThe results show that our method provides competitive performance compared with\nexisting alternative methods. Selective Convolutional Neural Network (S-CNN) is\na simple and fast algorithm, it introduces a new way to do unsupervised feature\nlearning, and it provides discriminative features which generalize well.","url_abs":"http://arxiv.org/abs/1606.02210v1","url_pdf":"http://arxiv.org/pdf/1606.02210v1.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":[],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"object-recognition","task_name":"Object Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-stl-10","task":"Image Classification","dataset":"STL-10","model":"S-CNN","rank_in_archive_order":102,"of":117,"metrics":{"Percentage correct":"61.94"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}