You Don't Need Domain-Specific Data Augmentations When Scaling Self-Supervised Learning
This work addresses the problem of reducing reliance on complex augmentations for researchers and practitioners in computer vision, though it is incremental as it builds on existing models like DINOv2.
The paper challenges the necessity of hand-crafted data augmentations in self-supervised learning with joint-embedding architectures, showing that using only cropping without resizing can achieve state-of-the-art results when trained on large datasets, as demonstrated with DINOv2.
Self-Supervised learning (SSL) with Joint-Embedding Architectures (JEA) has led to outstanding performances. All instantiations of this paradigm were trained using strong and well-established hand-crafted data augmentations, leading to the general belief that they are required for the proper training and performance of such models. On the other hand, generative reconstruction-based models such as BEIT and MAE or Joint-Embedding Predictive Architectures such as I-JEPA have shown strong performance without using data augmentations except masking. In this work, we challenge the importance of invariance and data-augmentation in JEAs at scale. By running a case-study on a recent SSL foundation model - DINOv2 - we show that strong image representations can be obtained with JEAs and only cropping without resizing provided the training data is large enough, reaching state-of-the-art results and using the least amount of augmentation in the literature. Through this study, we also discuss the impact of compute constraints on the outcomes of experimental deep learning research, showing that they can lead to very different conclusions.