We investigate the potential of learning visual representations using synthetic images
generated by text-to-image models. This is a natural question in the light of the excellent …

Recent significant advances in text-to-image models unlock the possibility of training vision
systems using synthetic images potentially overcoming the difficulty of collecting curated …

Massive web datasets play a key role in the success of large vision-language models like
CLIP and Flamingo. However, the raw web data is noisy, and existing filtering methods to …

We introduce SynCLR a novel approach for learning visual representations exclusively from
synthetic images without any real data. We synthesize a large dataset of image captions …

Utilizing auxiliary outlier datasets to regularize the machine learning model has
demonstrated promise for out-of-distribution (OOD) detection and safe prediction. Due to the …

Seismic advances in generative AI algorithms for imagery, text, and other data types has led
to the temptation to use synthetic data to train next-generation models. Repeating this …

Preparing training data for deep vision models is a labor-intensive task. To address this,
generative models have emerged as an effective solution for generating synthetic data …

Semantic segmentation has witnessed tremendous progress due to the proposal of various
advanced network architectures. However, they are extremely hungry for delicate …

Current perceptual similarity metrics operate at the level of pixels and patches. These
metrics compare images in terms of their low-level colors and textures, but fail to capture mid …

Recent research on robustness has revealed significant performance gaps between neural
image classifiers trained on datasets that are similar to the test set, and those that are from a …