Aligning machine and human visual representations across abstraction levels.

Abstract

Deep neural networks have achieved success across a wide range of applications, including as models of human behaviour and neural representations in vision tasks^1,2. However, neural network training and human learning differ in fundamental ways, and neural networks often fail to generalize as robustly as humans do^3,4, raising questions regarding the similarity of their underlying representations. We need to determine what is missing for modern learning systems to exhibit more human-aligned behaviour. Here we highlight a key misalignment between vision models and humans: whereas human conceptual knowledge is hierarchically organized from fine- to coarse-scale distinctions (for example, ref. ⁵), model representations do not accurately capture all these levels of abstraction. To address this misalignment, we first train a teacher model to imitate human judgements, then transfer human-aligned structure from its representations to refine the representations of pretrained state-of-the-art vision foundation models via fine-tuning. These human-aligned models more accurately approximate human behaviour and uncertainty across a wide range of similarity tasks, including a dataset of human judgements spanning multiple levels of semantic abstractions. They also perform better on a diverse set of machine learning tasks, increasing generalization and out-of-distribution robustness. Thus, infusing neural networks with additional human knowledge yields a best-of-both-worlds representation that is both more consistent with human cognitive judgements and more practically useful, paving the way towards more robust, interpretable and human-aligned artificial intelligence systems.