Better artificial intelligence does not mean better models of biology
This work highlights a critical divergence for neuroscience and vision science, indicating that incremental improvements in AI may not translate to biological insights.
The study found that as deep neural networks achieve human or superhuman accuracy on vision benchmarks, their alignment with primate perception and neural responses is plateauing or worsening, challenging the assumption that AI progress leads to better biological models.
Deep neural networks (DNNs) once showed increasing alignment with primate perception and neural responses as they improved on vision benchmarks, raising hopes that advances in AI would yield better models of biological vision. However, we show across three benchmarks that this alignment is now plateauing - and in some cases worsening - as DNNs scale to human or superhuman accuracy. This divergence may reflect the adoption of visual strategies that differ from those used by primates. These findings challenge the view that progress in artificial intelligence will naturally translate to neuroscience. We argue that vision science must chart its own course, developing algorithms grounded in biological visual systems rather than optimizing for benchmarks based on internet-scale datasets.