Exploring the Limits of Large Scale Pre-training
arXiv:2110.02095
Abstract
Recent developments in large-scale machine learning suggest that by scaling up data, model size and training time properly, one might observe that improvements in pre-training would transfer favorably to most downstream tasks. In this work, we systematically study this phenomena and establish that, as we increase the upstream accuracy, the performance of downstream tasks saturates. In particular, we investigate more than 4800 experiments on Vision Transformers, MLP-Mixers and ResNets with number of parameters ranging from ten million to ten billion, trained on the largest scale of available image data (JFT, ImageNet21K) and evaluated on more than 20 downstream image recognition tasks. We propose a model for downstream performance that reflects the saturation phenomena and captures the nonlinear relationship in performance of upstream and downstream tasks. Delving deeper to understand the reasons that give rise to these phenomena, we show that the saturation behavior we observe is closely related to the way that representations evolve through the layers of the models. We showcase an even more extreme scenario where performance on upstream and downstream are at odds with each other. That is, to have a better downstream performance, we need to hurt upstream accuracy.
References in corpus (15)
- Learning Transferable Visual Models From Natural Language Supervision
- How transferable are features in deep neural networks?
- Language Models are Few-Shot Learners
- Scaling Laws for Neural Language Models
- MLP-Mixer: An all-MLP Architecture for Vision
- Revisiting ResNets: Improved Training and Scaling Strategies
- A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark
- Self-supervised Pretraining of Visual Features in the Wild
- Carbon Emissions and Large Neural Network Training
- Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization
- Scaling Laws for Transfer
- Scalable Transfer Learning with Expert Models
- Supervised Transfer Learning at Scale for Medical Imaging
- OmniNet: Omnidirectional Representations from Transformers
- Comparing Transfer and Meta Learning Approaches on a Unified Few-Shot Classification Benchmark