2026-09-20T23:15:41Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/115621 2023-07-11 col_2142_5131 col_2142_10761 com_2142_5130 com_2142_10755 com_2142_234

Adve, Vikram 2022-05 application/pdf en text Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2024-05-01 The student, Garvita Allabadi, accepted the attached license on 2022-04-28 at 19:01. The student, Garvita Allabadi, submitted this Thesis for approval on 2022-04-28 at 19:07. This Thesis was approved for publication on 2022-04-29 at 08:02. DSpace SAF Submission Ingestion Package generated from Vireo submission #17989 on 2022-11-11 at 12:12:14 Towards open world semi supervised detection Allabadi, Garvita 2022-04-29 Open world Semi supervised learning Object Detection Traditional object detection networks work with large amounts of labeled data and under the assumption of a closed set, such that the test data only contains instances of classes already seen in the training set. These assumptions are challenged when deploying these methods in the wild. In this work we introduce Open World Semi Supervised Object Detection (OWSSD), a semi supervised learning framework that works in the open world setup. OWSSD effectively captures the novelty of unseen data compared to seen data and updates the detection framework to discover new classes on the fly. Thesis eng https://hdl.handle.net/2142/115621 Copyright 2022 Garvita Allabadi M.S. Thesis Computer Science University of Illinois at Urbana-Champaign Computer Science