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 …

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 …

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 …

A key theme in the past decade has been that when large neural networks and large
datasets combine they can produce remarkable results. In deep reinforcement learning (RL) …

In this paper, we introduce a large Multi-Attribute and Language Search dataset for text-
based person retrieval, called MALS, and explore the feasibility of performing pre-training on …

Acquiring high-quality data for training discriminative models is a crucial yet challenging
aspect of building effective predictive systems. In this paper, we present Diffusion Inversion …

Intrinsic images, in the original sense, are image-like maps of scene properties like depth,
normal, albedo, or shading. This paper demonstrates that StyleGAN can easily be induced …