Generalization Bounds for Deep Transfer Learning Using Majority Predictor Accuracy
Not on the map. Why?
Abstract (arXiv)
We analyze new generalization bounds for deep learning models trained by transfer learning from a source to a target task. Our bounds utilize a quantity called the majority predictor accuracy, which can be computed efficiently from data. We show that our theory is useful in practice since it implies that the majority predictor accuracy can be used as a transferability measure, a fact that is also validated by our experiments.
Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 13 of its 21 references that are in the map. First posted on arXiv 13 Sep 2022.
Builds on
13 of 21 references.
References · 13
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2016Understanding deep learning requires rethinking generalizationcited by 1,657
- 2017Spectrally-normalized margin bounds for neural networkscited by 681
- 2016Deep Transfer Learning with Joint Adaptation Networkscited by 609
- 2014CNN Features off-the-shelf: an Astounding Baseline for Recognitioncited by 316
- 2020LEEP: A New Measure to Evaluate Transferability of Learned Representationscited by 182
- 2021LogME: Practical Assessment of Pre-trained Models for Transfer Learningcited by 168
- 2019Transferability and Hardness of Supervised Classification Taskscited by 125
- 2019Regularized Learning for Domain Adaptation under Label Shiftscited by 118
- 2019Toward Understanding Catastrophic Forgetting in Continual Learningcited by 67
- 2021OTCE: A Transferability Metric for Cross-Domain Cross-Task Representationscited by 62
- 2019FixyNN: Efficient Hardware for Mobile Computer Vision via Transfer Learningcited by 10
1 more
- 2021Exploiting a Zoo of Checkpoints for Unseen Taskscited by 3
Built on by
Citing papers per year: 2023: 3; 2024: 0; 2025: 0; 2026: 1.
4 papers.