Finding Balance in Neural Architecture Search: Towards Optimal and Resource-Efficient Task Branching in Multi-Task Networks
2024 (English)Independent thesis Advanced level (degree of Master (Two Years)), 28 HE credits
Student thesis
Abstract [en]
Similar to how we humans use prior knowledge from one skill when learning new ones, multi-task networks can leverage similarities between different tasks to enhance learning speed. By acknowledging and leveraging common features across tasks, multi-task networks can be more efficient when learning and are able to generalize better. However, due to the technological advancements in deep learning, the modern architecture of such networks can be highly complex and vary significantly, so finding an optimal architecture is far from trivial. To handle this problem, we have utilized different methods to limit the search space and find the suitable architectural designs given a varying number of tasks. Through a comprehensive analysis of neural network structures and loss weighting strategies, the thesis contributes valuable insights into achieving a suitable trade-off between resource usage and task performance, paving the way for more effective and resource-conscious multi-task network designs.
Place, publisher, year, edition, pages
2024. , p. 38
Series
LiTH-ISY-EX--24/5650--SE
Keywords [en]
computer vision, multi-task learning, machine learning, neural architecture search, BMTAS, Shapley-NAS
National Category
Computer graphics and computer vision
Identifiers
URN: urn:nbn:se:liu:diva-205900OAI: oai:DiVA.org:liu-205900DiVA, id: diva2:1883281
External cooperation
Qualcomm
Subject / course
Computer Vision Laboratory
Presentation
2024-06-03, Transformen, Olaus Magnus väg, 583 30, Linköping, 10:15 (English)
Supervisors
Examiners
2024-07-112024-07-092025-02-07Bibliographically approved