Transfer learning aims to leverage models pre-trained on source data to efficiently adapt to target setting, where only limited data are available for model fine-tuning. Recent works …
Transfer of pre-trained representations improves sample efficiency and simplifies hyperparameter tuning when training deep neural networks for vision. We revisit the …
F Zhuang, X Cheng, P Luo, SJ Pan… - Twenty-fourth international …, 2015 - cse.cuhk.edu.hk
Transfer learning has attracted a lot of attention in the past decade. One crucial research issue in transfer learning is how to find a good representation for instances of different …
Transfer learning has gained a lot of attention and interest in the past decade. One crucial research issue in transfer learning is how to find a good representation for instances of …
B Liu, Y Cai, Y Guo, X Chen - Proceedings of the AAAI conference on …, 2021 - ojs.aaai.org
The increasing of pre-trained models has significantly facilitated the performance on limited data tasks with transfer learning. However, progress on transfer learning mainly focuses on …
Transfer learning aims at improving the performance of target learners on target domains by transferring the knowledge contained in different but related source domains. In this way, the …
A Wang, O Russakovsky - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
Transfer learning is beneficial by allowing the expressive features of models pretrained on large-scale datasets to be finetuned for the target task of smaller, more domain-specific …
Transfer of pre-trained representations improves sample efficiency and simplifies hyperparameter tuning when training deep neural networks for vision. We revisit the …
B Wang, J Mendez, M Cai… - Advances in neural …, 2019 - proceedings.neurips.cc
We propose a new principle for transfer learning, based on a straightforward intuition: if two domains are similar to each other, the model trained on one domain should also perform …