Computing a human-like reaction time metric from stable recurrent vision models
This work addresses the problem of temporal alignment between AI models and human behavior for researchers in computational neuroscience and AI, though it is incremental in extending existing alignment efforts.
The paper tackled the challenge of aligning deep neural networks with human visual decision-making by developing a novel metric to compute reaction times from recurrent vision models, demonstrating alignment with human reaction times across four visual tasks.
The meteoric rise in the adoption of deep neural networks as computational models of vision has inspired efforts to "align" these models with humans. One dimension of interest for alignment includes behavioral choices, but moving beyond characterizing choice patterns to capturing temporal aspects of visual decision-making has been challenging. Here, we sketch a general-purpose methodology to construct computational accounts of reaction times from a stimulus-computable, task-optimized model. Specifically, we introduce a novel metric leveraging insights from subjective logic theory summarizing evidence accumulation in recurrent vision models. We demonstrate that our metric aligns with patterns of human reaction times for stimulus manipulations across four disparate visual decision-making tasks spanning perceptual grouping, mental simulation, and scene categorization. This work paves the way for exploring the temporal alignment of model and human visual strategies in the context of various other cognitive tasks toward generating testable hypotheses for neuroscience. Links to the code and data can be found on the project page: https://serre-lab.github.io/rnn_rts_site.