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 …
X Du, Y Sun, J Zhu, Y Li - Advances in Neural Information …, 2024 - proceedings.neurips.cc
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 …
Q Nguyen, T Vu, A Tran… - Advances in Neural …, 2024 - proceedings.neurips.cc
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 …
C Lu, P Ball, YW Teh… - Advances in Neural …, 2024 - proceedings.neurips.cc
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) …
S Yang, Y Zhou, Z Zheng, Y Wang, L Zhu… - Proceedings of the 31st …, 2023 - dl.acm.org
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 …
Y Zhou, H Sahak, J Ba - arXiv preprint arXiv:2305.15316, 2023 - arxiv.org
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 …