Abstract: In recent years, the success of large-scale vision-language models (VLMs) such as CLIP has led to their increased usage in various computer vision tasks. These models enable zero-shot ...
Old-school C-Clamps are in every toolbox, but they have a lot more uses than just clamping things together while you work.
Abstract: This work explores capabilities of the pre-trained CLIP vision-language model to identify satellite images affected by clouds. Several approaches to using the model to perform cloud presence ...