# Emergence of Fixational and Saccadic Movements in a Multi-Level Recurrent Attention Model for Vision

arXiv: https://arxiv.org/abs/2505.13191 · HTML: https://mlsanity.com/paper/2505.13191/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 35 references that are in the map.
- First posted on arXiv 19 May 2025.

## Builds on (most cited first, 9 of 9)

- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://mlsanity.com/paper/1502.03044/) (2015)
- [Recurrent Models of Visual Attention](https://mlsanity.com/paper/1406.6247/) (2014)
- [Active Object Localization with Deep Reinforcement Learning](https://mlsanity.com/paper/1511.06015/) (2015)
- [Exploring Human-like Attention Supervision in Visual Question Answering](https://mlsanity.com/paper/1709.06308/) (2017)
- [Saccader: Improving Accuracy of Hard Attention Models for Vision](https://mlsanity.com/paper/1908.07644/) (2019)
- [Dynamic Computational Time for Visual Attention](https://mlsanity.com/paper/1703.10332/) (2017)
- [Active Sensing with Predictive Coding and Uncertainty Minimization](https://mlsanity.com/paper/2307.00668/) (2023)

## Built on by (most cited first, 3 of 3)

- [Debiasing Central Fixation Confounds Reveals a Peripheral "Sweet Spot" for Human-like Scanpaths in Hard-Attention Vision](https://mlsanity.com/paper/2602.14834/) (2026)
- [EVA: Bridging Performance and Human Alignment in Hard-Attention Vision Models for Image Classification](https://mlsanity.com/paper/2603.27340/) (2026)
- [HiResNets: Native Full-HD Video Recognition with Foveal Residual Streams](https://mlsanity.com/paper/2608.02140/) (2026)

## Abstract (arXiv)

Inspired by foveal vision, hard attention models promise interpretability and parameter economy. However, existing models like the Recurrent Model of Visual Attention (RAM) and Deep Recurrent Attention Model (DRAM) failed to model the hierarchy of human vision system, that compromise on the visual exploration dynamics. As a result, they tend to produce attention that are either overly fixational or excessively saccadic, diverging from human eye movement behavior. In this paper, we propose a Multi-Level Recurrent Attention Model (MRAM), a novel hard attention framework that explicitly models the neural hierarchy of human visual processing. By decoupling the function of glimpse location generation and task execution in two recurrent layers, MRAM emergent a balanced behavior between fixation and saccadic movement. Our results show that MRAM not only achieves more human-like attention dynamics, but also consistently outperforms CNN, RAM and DRAM baselines on standard image classification benchmarks.