Teaching AI to see the world more like we do
Google DeepMind
Researchers developed a method to reorganize how AI vision models represent visual information so they align better with human perception. The technique uses a three-step process involving a teacher model trained on the THINGS dataset of human judgments, which generates millions of synthetic training examples to fine-tune student models. Models trained this way show improved performance on cognitive tasks, few-shot learning, and robustness to image distribution shifts.
Why it matters
Our new paper analyzes the important ways AI systems organize the visual world differently from humans.
