Just five minutes of training significantly improved people's ability to detect AI-generated faces and synthetic facial images.
Introduced in the paper "Roboflow 100-VL: A Multi-Domain Object Detection Benchmark for Vision-Language Models", RF100-VL is a large-scale collection of 100 multi-modal datasets with diverse concepts ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback