# Computing a human-like reaction time metric from stable recurrent vision models

arXiv: https://arxiv.org/abs/2306.11582 · HTML: https://mlsanity.com/paper/2306.11582/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 68 references that are in the map.
- First posted on arXiv 20 Jun 2023.

## Builds on (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting](https://mlsanity.com/paper/1506.04214/) (2015)
- [Evidential Deep Learning to Quantify Classification Uncertainty](https://mlsanity.com/paper/1806.01768/) (2018)
- [Adaptive Computation Time for Recurrent Neural Networks](https://mlsanity.com/paper/1603.08983/) (2016)
- [Partial success in closing the gap between human and machine vision](https://mlsanity.com/paper/2106.07411/) (2021)
- [Conditional Computation in Neural Networks for faster models](https://mlsanity.com/paper/1511.06297/) (2015)
- [Spatially Adaptive Computation Time for Residual Networks](https://mlsanity.com/paper/1612.02297/) (2016)
- [Learning long-range spatial dependencies with horizontal gated-recurrent units](https://mlsanity.com/paper/1805.08315/) (2018)
- [Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimation](https://mlsanity.com/paper/2110.03051/) (2021)
- [Harmonizing the object recognition strategies of deep neural networks with humans](https://mlsanity.com/paper/2211.04533/) (2022)
- [Recurrent Batch Normalization](https://mlsanity.com/paper/1603.09025/) (2016)
- [Biologically inspired protection of deep networks from adversarial attacks](https://mlsanity.com/paper/1703.09202/) (2017)
- [Learning model-based planning from scratch](https://mlsanity.com/paper/1707.06170/) (2017)
- [Stable and expressive recurrent vision models](https://mlsanity.com/paper/2005.11362/) (2020)
- [Tracking Without Re-recognition in Humans and Machines](https://mlsanity.com/paper/2105.13351/) (2021)
- [From deep learning to mechanistic understanding in neuroscience: the structure of retinal prediction](https://mlsanity.com/paper/1912.06207/) (2019)
- [Deep Sequential Neural Network](https://mlsanity.com/paper/1410.0510/) (2014)
- [Anytime Prediction as a Model of Human Reaction Time](https://mlsanity.com/paper/2011.12859/) (2020)
- [Image Features Influence Reaction Time: A Learned Probabilistic Perceptual Model for Saccade Latency](https://mlsanity.com/paper/2205.02437/) (2022)

## Built on by (most cited first, 6 of 6)

- [A comparison between humans and AI at recognizing objects in unusual poses](https://mlsanity.com/paper/2402.03973/) (2024)
- [RTify: Aligning Deep Neural Networks with Human Behavioral Decisions](https://mlsanity.com/paper/2411.03630/) (2024)
- [Inferring response times of perceptual decisions with Poisson variational autoencoders](https://mlsanity.com/paper/2511.11480/) (2025)
- [The Role of Recurrency in Image Segmentation for Noisy and Limited Sample Settings](https://mlsanity.com/paper/2412.15734/) (2024)
- [Deep Recurrence for Dynamical Segmentation Models](https://mlsanity.com/paper/2507.10143/) (2025)
- [Deep Feedback Models](https://mlsanity.com/paper/2509.15905/) (2025)

## Abstract (arXiv)

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.