# Dynamic Computational Time for Visual Attention

arXiv: https://arxiv.org/abs/1703.10332 · HTML: https://mlsanity.com/paper/1703.10332/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Mar 2017.

## Built on by (most cited first, 23 of 23)

- [Dynamic Neural Networks: A Survey](https://mlsanity.com/paper/2102.04906/) (2021)
- [MOOD: Multi-level Out-of-distribution Detection](https://mlsanity.com/paper/2104.14726/) (2021)
- [Differentiable Patch Selection for Image Recognition](https://mlsanity.com/paper/2104.03059/) (2021)
- [Variational Information Pursuit for Interpretable Predictions](https://mlsanity.com/paper/2302.02876/) (2023)
- [Human Attention in Fine-grained Classification](https://mlsanity.com/paper/2111.01628/) (2021)
- [Internally Rewarded Reinforcement Learning](https://mlsanity.com/paper/2302.00270/) (2023)
- [Computation-efficient Deep Learning for Computer Vision: A Survey](https://mlsanity.com/paper/2308.13998/) (2023)
- [A Probabilistic Hard Attention Model For Sequentially Observed Scenes](https://mlsanity.com/paper/2111.07534/) (2021)
- [SALISA: Saliency-based Input Sampling for Efficient Video Object Detection](https://mlsanity.com/paper/2204.02397/) (2022)
- [BirdSAT: Cross-View Contrastive Masked Autoencoders for Bird Species Classification and Mapping](https://mlsanity.com/paper/2310.19168/) (2023)
- [Re-rank Coarse Classification with Local Region Enhanced Features for Fine-Grained Image Recognition](https://mlsanity.com/paper/2102.09875/) (2021)
- [Fine-Grained Visual Classification using Self Assessment Classifier](https://mlsanity.com/paper/2205.10529/) (2022)
- [Boosted Dynamic Neural Networks](https://mlsanity.com/paper/2211.16726/) (2022)
- [Foveation in the Era of Deep Learning](https://mlsanity.com/paper/2312.01450/) (2023)
- [Learning Canonical 3D Object Representation for Fine-Grained Recognition](https://mlsanity.com/paper/2108.04628/) (2021)
- [Progressive Co-Attention Network for Fine-grained Visual Classification](https://mlsanity.com/paper/2101.08527/) (2021)
- [Locality-aware Concept Bottleneck Model](https://mlsanity.com/paper/2508.14562/) (2025)
- [SlowFormer: Universal Adversarial Patch for Attack on Compute and Energy Efficiency of Inference Efficient Vision Transformers](https://mlsanity.com/paper/2310.02544/) (2023)
- [Emergence of Fixational and Saccadic Movements in a Multi-Level Recurrent Attention Model for Vision](https://mlsanity.com/paper/2505.13191/) (2025)
- [Sparsely ensembled convolutional neural network classifiers via reinforcement learning](https://mlsanity.com/paper/2102.03921/) (2021)
- [E^2TAD: An Energy-Efficient Tracking-based Action Detector](https://mlsanity.com/paper/2204.04416/) (2022)
- [EnGraf-Net: Multiple Granularity Branch Network with Fine-Coarse Graft Grained for Classification Task](https://mlsanity.com/paper/2509.21061/) (2025)
- [Exploring Budgeted Image Classification with Content-Sensitive Resource Allocation](https://mlsanity.com/paper/2607.23997/) (2026)

## Abstract (arXiv)

We propose a dynamic computational time model to accelerate the average processing time for recurrent visual attention (RAM). Rather than attention with a fixed number of steps for each input image, the model learns to decide when to stop on the fly. To achieve this, we add an additional continue/stop action per time step to RAM and use reinforcement learning to learn both the optimal attention policy and stopping policy. The modification is simple but could dramatically save the average computational time while keeping the same recognition performance as RAM. Experimental results on CUB-200-2011 and Stanford Cars dataset demonstrate the dynamic computational model can work effectively for fine-grained image recognition.The source code of this paper can be obtained from https://github.com/baidu-research/DT-RAM