Deep learning has significantly advanced image analysis across diverse domains but often depends on large, annotated datasets for success. Transfer learning addresses this challenge by utilizing pre-trained models to tackle new tasks with limited labeled data. However, discrepancies between source and target domains can hinder effective transfer learning. We introduce BioTune, a novel adaptive fine-tuning technique utilizing evolutionary optimization. BioTune enhances transfer learning by optimally choosing which layers to freeze and adjusting learning rates for unfrozen layers. Through extensive evaluation on nine image classification datasets, spanning natural and specialized domains such as medical imaging, BioTune demonstrates superior accuracy and efficiency over state-of-the-art fine-tuning methods, including AutoRGN and LoRA, highlighting its adaptability to various data characteristics and distribution changes. Additionally, BioTune consistently achieves top performance across four different CNN architectures, underscoring its flexibility. Ablation studies provide valuable insights into the impact of BioTune's key components on overall performance. The source code is available at https://github.com/davilac/BioTune.
Bio-inspired Color Constancy: From Gray Anchoring Theory to Gray Pixel Methods
MOE Key Laboratory for Neuroinformation, School of Life Science and Technology, University of Electronic Science and Technology of China(教育部神经信息学重点实验室,生命科学与技术学院,电子科学与技术大学);School of Electronic Engineering and Automation, Guilin University of Electronic Technology(电子工程与自动化学院,桂林电子科技大学)
CL-BioGAN: Biologically-Inspired Cross-Domain Continual Learning for Hyperspectral Anomaly Detection
Key Laboratory of Collaborative Intelligence Systems, Ministry of Education, School of Computer Science and Technology, Xidian University(协同智能系统重点实验室、教育部、计算机科学与技术学院、西安电子科技大学);Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China, School of Artificial Intelligence, Xidian University(智能感知与图像理解重点实验室、教育部、人工智能学院、西安电子科技大学);Key Laboratory of Collaborative Intelligence Systems, Ministry of Education, Xidian University(协同智能系统重点实验室、教育部、西安电子科技大学)
Transfer learning optimization based on evolutionary selective fine tuning
Department of Micro-Nano Mechanical Science and Engineering, Nagoya University(名古屋大学微纳米机械科学与工程系);Institutes of Innovation for Future Society, Nagoya University(面向未来社会的创新研究院)
Bio-inspired AI: Integrating Biological Complexity into Artificial Intelligence
McGovern Institute for Brain Research, MIT(麻省理工学院麦戈文脑科学研究所);Allen Discovery Center at Tufts University(塔夫茨大学艾伦发现中心);Center for Brains, Minds, and Machines, MIT(麻省理工学院脑、心智与机器中心);Wyss Institute for Biologically Inspired Engineering, Harvard University(哈佛大学威斯生物启发工程研究所)
AIT Austrian Institute of Technology(奥地利理工学院);University of Zurich(苏黎世大学);ETH Zurich(苏黎世联邦理工学院);Western Sydney University(西悉尼大学);University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)