{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T06:38:55Z","timestamp":1725518335879},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7]]},"abstract":"<jats:p>Semi-weakly supervised semantic segmentation (SWSSS) aims to train a model to identify objects in images based on a small number of images with pixel-level labels, and many more images with only image-level labels. Most existing SWSSS algorithms extract pixel-level pseudo-labels from an image classifier - a very difficult task to do well, hence requiring complicated architectures and extensive hyperparameter tuning on fully-supervised validation sets. We propose a method called prediction filtering, which instead of extracting pseudo-labels, just uses the classifier as a classifier: it ignores any segmentation predictions from classes which the classifier is confident are not present. Adding this simple post-processing method to baselines gives results competitive with or better than prior SWSSS algorithms. Moreover, it is compatible with pseudo-label methods: adding prediction filtering to existing SWSSS algorithms further improves segmentation performance.<\/jats:p>","DOI":"10.24963\/ijcai.2022\/389","type":"proceedings-article","created":{"date-parts":[[2022,7,16]],"date-time":"2022-07-16T02:55:56Z","timestamp":1657940156000},"page":"2805-2811","source":"Crossref","is-referenced-by-count":3,"title":["One Weird Trick to Improve Your Semi-Weakly Supervised Semantic Segmentation Model"],"prefix":"10.24963","author":[{"given":"Wonho","family":"Bae","sequence":"first","affiliation":[{"name":"University of British Columbia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junhyug","family":"Noh","sequence":"additional","affiliation":[{"name":"Lawrence Livermore National Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Milad","family":"Jalali Asadabadi","sequence":"additional","affiliation":[{"name":"University of British Columbia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Danica J.","family":"Sutherland","sequence":"additional","affiliation":[{"name":"University of British Columbia"},{"name":"Alberta Machine Intelligence Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"10584","event":{"number":"31","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"acronym":"IJCAI-2022","name":"Thirty-First International Joint Conference on Artificial Intelligence {IJCAI-22}","start":{"date-parts":[[2022,7,23]]},"theme":"Artificial Intelligence","location":"Vienna, Austria","end":{"date-parts":[[2022,7,29]]}},"container-title":["Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T11:09:27Z","timestamp":1658142567000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2022\/389"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2022,7]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2022\/389","relation":{},"subject":[],"published":{"date-parts":[[2022,7]]}}}