{"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/a-new-benchmark-and-progress-toward-improved","title":"A New Benchmark and Progress Toward Improved Weakly Supervised Learning","arxiv_id":"1807.00126","date":"2018-06-30","proceeding":null,"authors":["Jason Ramapuram","Russ Webb"],"abstract":"Knowledge Matters: Importance of Prior Information for Optimization [7], by\nGulcehre et. al., sought to establish the limits of current black-box, deep\nlearning techniques by posing problems which are difficult to learn without\nengineering knowledge into the model or training procedure. In our work, we\ncompletely solve the previous Knowledge Matters problem using a generic model,\npose a more difficult and scalable problem, All-Pairs, and advance this new\nproblem by introducing a new learned, spatially-varying histogram model called\nTypeNet which outperforms conventional models on the problem. We present\nresults on All-Pairs where our model achieves 100% test accuracy while the best\nResNet models achieve 79% accuracy. In addition, our model is more than an\norder of magnitude smaller than Resnet-34. The challenge of solving\nlarger-scale All-Pairs problems with high accuracy is presented to the\ncommunity for investigation.","url_abs":"http://arxiv.org/abs/1807.00126v2","url_pdf":"http://arxiv.org/pdf/1807.00126v2.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":"a-new-benchmark-and-progress-toward-improved","repo_url":"https://github.com/apple/ml-all-pairs","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"all","task_name":"All"},{"task_slug":"weakly-supervised-learning","task_name":"Weakly-supervised Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}