{"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/interactive-classification-for-deep-learning","title":"Interactive Classification for Deep Learning Interpretation","arxiv_id":"1806.05660","date":"2018-06-14","proceeding":null,"authors":["Ángel Alexander Cabrera","Fred Hohman","Jason Lin","Duen Horng Chau"],"abstract":"We present an interactive system enabling users to manipulate images to\nexplore the robustness and sensitivity of deep learning image classifiers.\nUsing modern web technologies to run in-browser inference, users can remove\nimage features using inpainting algorithms and obtain new classifications in\nreal time, which allows them to ask a variety of \"what if\" questions by\nexperimentally modifying images and seeing how the model reacts. Our system\nallows users to compare and contrast what image regions humans and machine\nlearning models use for classification, revealing a wide range of surprising\nresults ranging from spectacular failures (e.g., a \"water bottle\" image becomes\na \"concert\" when removing a person) to impressive resilience (e.g., a \"baseball\nplayer\" image remains correctly classified even without a glove or base). We\ndemonstrate our system at The 2018 Conference on Computer Vision and Pattern\nRecognition (CVPR) for the audience to try it live. Our system is open-sourced\nat https://github.com/poloclub/interactive-classification. A video demo is\navailable at https://youtu.be/llub5GcOF6w.","url_abs":"http://arxiv.org/abs/1806.05660v2","url_pdf":"http://arxiv.org/pdf/1806.05660v2.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":"interactive-classification-for-deep-learning","repo_url":"https://github.com/poloclub/interactive-classification","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"classification","task_name":"General Classification"}],"methods":[{"method_slug":"glove","method_name":"GloVe"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}