2026-09-20T22:23:49Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/120293 2023-09-05 col_2142_5131 col_2142_10761 com_2142_5130 com_2142_10755 com_2142_234

Hoiem, Derek 2023-05 application/pdf en text Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2023-09-01 without embargo terms The student, Weijie Lyu, accepted the attached license on 2023-04-19 at 18:52. The student, Weijie Lyu, submitted this Thesis for approval on 2023-04-19 at 21:35. This Thesis was approved for publication on 2023-04-20 at 14:11. DSpace SAF Submission Ingestion Package generated from Vireo submission #19053 on 2023-09-01 at 17:09:04 MACON: memory-augmented continual learning for open-world classification Lyu, Weijie 2023-04-20 Continual Learning Open-world Recognition Open-vocabulary Classification Memory-augmented Neural Network Emerging concepts and rapidly changing environments necessitate AI models that can quickly adapt to new scenarios without losing their inherited capabilities. Large foundation models like CLIP offer a strong zero-shot learning baseline under an open-vocabulary classification scenario. However, their massive training data makes re-training or fine-tuning impractical without sacrificing zero-shot performance. We introduce Memory-Augmented CONtinual learning (MACON), a novel framework for addressing open-world continual learning challenges. The core idea is to augment foundation models, such as CLIP, with memory to provide context and flexibility for better decision-making and prevention of catastrophic forgetting. We propose various memory retrieval methods tailored to different continual learning scenarios. Our results demonstrate that MACON exhibits fast adaptation capabilities, minimal forgetting issues, and robust generalization abilities, making it suitable for a wide range of open-world applications. Thesis eng https://hdl.handle.net/2142/120293 Copyright 2023 Weijie Lyu M.S. Thesis Computer Science University of Illinois at Urbana-Champaign Computer Science