{"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/radam-texture-recognition-through-randomized-1","title":"RADAM: Texture Recognition through Randomized Aggregated Encoding of Deep Activation Maps","arxiv_id":"2303.04554","date":"2023-03-08","proceeding":null,"authors":["Leonardo Scabini","Kallil M. Zielinski","Lucas C. Ribas","Wesley N. Gonçalves","Bernard De Baets","Odemir M. Bruno"],"abstract":"Texture analysis is a classical yet challenging task in computer vision for which deep neural networks are actively being applied. Most approaches are based on building feature aggregation modules around a pre-trained backbone and then fine-tuning the new architecture on specific texture recognition tasks. Here we propose a new method named \\textbf{R}andom encoding of \\textbf{A}ggregated \\textbf{D}eep \\textbf{A}ctivation \\textbf{M}aps (RADAM) which extracts rich texture representations without ever changing the backbone. The technique consists of encoding the output at different depths of a pre-trained deep convolutional network using a Randomized Autoencoder (RAE). The RAE is trained locally to each image using a closed-form solution, and its decoder weights are used to compose a 1-dimensional texture representation that is fed into a linear SVM. This means that no fine-tuning or backpropagation is needed. We explore RADAM on several texture benchmarks and achieve state-of-the-art results with different computational budgets. Our results suggest that pre-trained backbones may not require additional fine-tuning for texture recognition if their learned representations are better encoded.","url_abs":"https://arxiv.org/abs/2303.04554v1","url_pdf":"https://arxiv.org/pdf/2303.04554v1.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":"radam-texture-recognition-through-randomized-1","repo_url":"https://github.com/scabini/RADAM","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"texture-classification","task_name":"Texture Classification"}],"methods":[{"method_slug":"rae","method_name":"RAE"},{"method_slug":"radam","method_name":"RAdam"},{"method_slug":"svm","method_name":"SVM"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-dtd","task":"Image Classification","dataset":"DTD","model":"RADAM (ConvNeXt-L)","rank_in_archive_order":2,"of":11,"metrics":{"Accuracy":"84.0"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-fmd-texture","task":"Image Classification","dataset":"FMD (materials)","model":"RADAM (ConvNeXt-L)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy (%)":"95.2"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-kth-tips2","task":"Image Classification","dataset":"KTH-TIPS2","model":"RADAM (ConvNeXt-XL)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy (%)":"94.4"},"uses_additional_data":true}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}