Lizhen Zhu

Mar 26, 2024 | cell.com | Lizhen Zhu |James Wang |Wonseuk Lee |Brad Wyble

Highlights•Created an approach that uses spatial context as a similarity signal•A method for constructing image datasets using an environmental-sampling agent•Training with contextual information improves state of the art in contrastive learning•Simulated data provide new forms of physically realistic augmentationsThe bigger pictureDespite being trained on extensive datasets, current computer vision systems lag behind human children in learning about the visual world.

May 12, 2023 | mdpi.com | Lizhen Zhu |Xiaoying Li |Jun He |Xiaoping Zhou

This is an early access version, the complete PDF, HTML, and XML versions will be available soon.