Jianxin Wu

Rethinking Self-Supervised Learning: Small is Beautiful

2021 · arXiv (Cornell University)

Self-supervised learning (SSL), in particular contrastive learning, has made great progress in recent years. However, a common theme in these methods is that they inherit the learning paradigm from the supervised deep learning scenario. Current …

DTL: Disentangled Transfer Learning for Visual Recognition

2024 · Proceedings of the AAAI Conference on Artificial Intelligence

When pre-trained models become rapidly larger, the cost of fine-tuning on downstream tasks steadily increases, too. To economically fine-tune these models, parameter-efficient transfer learning (PETL) is proposed, which only tunes a tiny subset of trainable …