Learning Vision from Models Rivals Learning Vision from Data
This addresses the data scarcity issue for computer vision researchers by enabling training without real-world datasets, though it builds on existing synthetic generation methods.
The paper tackles the problem of learning visual representations without real data by using synthetic images and captions, achieving competitive performance in image classification and significant improvements in semantic segmentation, e.g., 6.2 and 4.3 mIoU gains over MAE and iBOT on ADE20k.
We introduce SynCLR, a novel approach for learning visual representations exclusively from synthetic images and synthetic captions, without any real data. We synthesize a large dataset of image captions using LLMs, then use an off-the-shelf text-to-image model to generate multiple images corresponding to each synthetic caption. We perform visual representation learning on these synthetic images via contrastive learning, treating images sharing the same caption as positive pairs. The resulting representations transfer well to many downstream tasks, competing favorably with other general-purpose visual representation learners such as CLIP and DINO v2 in image classification tasks. Furthermore, in dense prediction tasks such as semantic segmentation, SynCLR outperforms previous self-supervised methods by a significant margin, e.g., improving over MAE and iBOT by 6.2 and 4.3 mIoU on ADE20k for ViT-B/16.