Transfer Learning
Transfer learning leverages knowledge gained from training a model on one task (the source) to improve its performance on a related but different task (the target), addressing data scarcity and reducing computational costs. Current research focuses on optimizing source data selection, employing various deep learning architectures like CNNs, LSTMs, and Transformers, and exploring techniques like data augmentation and hyperparameter optimization to enhance transferability across diverse domains. This approach significantly impacts various fields, from improving the accuracy and efficiency of medical image analysis and natural language processing to enabling more robust and adaptable AI systems in resource-constrained environments.
Papers
Transfer Reinforcement Learning in Heterogeneous Action Spaces using Subgoal Mapping
Kavinayan P. Sivakumar, Yan Zhang, Zachary Bell, Scott Nivison, Michael M. Zavlanos
Transfer Learning on Transformers for Building Energy Consumption Forecasting -- A Comparative Study
Robert Spencer, Surangika Ranathunga, Mikael Boulic, Andries (Hennie) van Heerden, Teo Susnjak
FedGTST: Boosting Global Transferability of Federated Models via Statistics Tuning
Evelyn Ma, Chao Pan, Rasoul Etesami, Han Zhao, Olgica Milenkovic
Tracking Universal Features Through Fine-Tuning and Model Merging
Niels Horn, Desmond Elliott
Transfer Learning on Multi-Dimensional Data: A Novel Approach to Neural Network-Based Surrogate Modeling
Adrienne M. Propp, Daniel M. Tartakovsky
TransAgent: Transfer Vision-Language Foundation Models with Heterogeneous Agent Collaboration
Yiwei Guo, Shaobin Zhuang, Kunchang Li, Yu Qiao, Yali Wang
Selecting the Best Sequential Transfer Path for Medical Image Segmentation with Limited Labeled Data
Jingyun Yang, Jingge Wang, Guoqing Zhang, Yang Li
Transfer Learning for a Class of Cascade Dynamical Systems
Shima Rabiei, Sandipan Mishra, Santiago Paternain
Utilizing Transfer Learning and pre-trained Models for Effective Forest Fire Detection: A Case Study of Uttarakhand
Hari Prabhat Gupta, Rahul Mishra
On The Relationship between Visual Anomaly-free and Anomalous Representations
Riya Sadrani, Hrishikesh Sharma, Ayush Bachan