{"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/take-5-interpretable-image-classification","title":"Take 5: Interpretable Image Classification with a Handful of Features","arxiv_id":"2303.13166","date":"2023-03-23","proceeding":null,"authors":["Thomas Norrenbrock","Marco Rudolph","Bodo Rosenhahn"],"abstract":"Deep Neural Networks use thousands of mostly incomprehensible features to identify a single class, a decision no human can follow. We propose an interpretable sparse and low dimensional final decision layer in a deep neural network with measurable aspects of interpretability and demonstrate it on fine-grained image classification. We argue that a human can only understand the decision of a machine learning model, if the features are interpretable and only very few of them are used for a single decision. For that matter, the final layer has to be sparse and, to make interpreting the features feasible, low dimensional. We call a model with a Sparse Low-Dimensional Decision SLDD-Model. We show that a SLDD-Model is easier to interpret locally and globally than a dense high-dimensional decision layer while being able to maintain competitive accuracy. Additionally, we propose a loss function that improves a model's feature diversity and accuracy. Our more interpretable SLDD-Model only uses 5 out of just 50 features per class, while maintaining 97% to 100% of the accuracy on four common benchmark datasets compared to the baseline model with 2048 features.","url_abs":"https://arxiv.org/abs/2303.13166v2","url_pdf":"https://arxiv.org/pdf/2303.13166v2.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":"take-5-interpretable-image-classification","repo_url":"https://github.com/thomasnorr/q-senn","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"take-5-interpretable-image-classification","repo_url":"https://github.com/ThomasNorr/QPM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"fine-grained-image-classification","task_name":"Fine-Grained Image Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"interpretable-machine-learning","task_name":"Interpretable Machine Learning"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/interpretable-machine-learning-on-cub-200","task":"Interpretable Machine Learning","dataset":"CUB-200-2011","model":"SLDD-Model","rank_in_archive_order":2,"of":2,"metrics":{"Top 1 Accuracy":"85.7"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}