The Evolution of Out-of-Distribution Robustness Throughout Fine-Tuning
arXiv:2106.15831
Abstract
Although machine learning models typically experience a drop in performance on out-of-distribution data, accuracies on in- versus out-of-distribution data are widely observed to follow a single linear trend when evaluated across a testbed of models. Models that are more accurate on the out-of-distribution data relative to this baseline exhibit "effective robustness" and are exceedingly rare. Identifying such models, and understanding their properties, is key to improving out-of-distribution performance. We conduct a thorough empirical investigation of effective robustness during fine-tuning and surprisingly find that models pre-trained on larger datasets exhibit effective robustness during training that vanishes at convergence. We study how properties of the data influence effective robustness, and we show that it increases with the larger size, more diversity, and higher example difficulty of the dataset. We also find that models that display effective robustness are able to correctly classify 10% of the examples that no other current testbed model gets correct. Finally, we discuss several strategies for scaling effective robustness to the high-accuracy regime to improve the out-of-distribution accuracy of state-of-the-art models.
27 pages, 25 figures
References in corpus (9)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Learning Transferable Visual Models From Natural Language Supervision
- One weird trick for parallelizing convolutional neural networks
- Scaling Laws for Transfer
- The Effect of Natural Distribution Shift on Question Answering Models
- Model Similarity Mitigates Test Set Overuse
- Why do classifier accuracies show linear trends under distribution shift?