# PERTINENCE: Input-based Opportunistic Neural Network Dynamic Execution

arXiv: https://arxiv.org/abs/2507.01695 · HTML: https://mlsanity.com/paper/2507.01695/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 41 references that are in the map.
- First posted on arXiv 2 Jul 2025.

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [Once-for-All: Train One Network and Specialize it for Efficient Deployment](https://mlsanity.com/paper/1908.09791/) (2019)
- [Scaling Vision with Sparse Mixture of Experts](https://mlsanity.com/paper/2106.05974/) (2021)
- [BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks](https://mlsanity.com/paper/1709.01686/) (2017)
- [Dynamic Neural Networks: A Survey](https://mlsanity.com/paper/2102.04906/) (2021)
- [Slimmable Neural Networks](https://mlsanity.com/paper/1812.08928/) (2018)
- [A Survey of Model Compression and Acceleration for Deep Neural Networks](https://mlsanity.com/paper/1710.09282/) (2017)
- [Pruning and Quantization for Deep Neural Network Acceleration: A Survey](https://mlsanity.com/paper/2101.09671/) (2021)
- [Universally Slimmable Networks and Improved Training Techniques](https://mlsanity.com/paper/1903.05134/) (2019)
- [An Analysis of Deep Neural Network Models for Practical Applications](https://mlsanity.com/paper/1605.07678/) (2016)
- [Adaptive Inference through Early-Exit Networks: Design, Challenges and Directions](https://mlsanity.com/paper/2106.05022/) (2021)
- [Why should we add early exits to neural networks?](https://mlsanity.com/paper/2004.12814/) (2020)
- [Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gap](https://mlsanity.com/paper/2008.01475/) (2020)
- [HAPI: Hardware-Aware Progressive Inference](https://mlsanity.com/paper/2008.03997/) (2020)
- [MobiSR: Efficient On-Device Super-Resolution through Heterogeneous Mobile Processors](https://mlsanity.com/paper/1908.07985/) (2019)
- [Routers in Vision Mixture of Experts: An Empirical Study](https://mlsanity.com/paper/2401.15969/) (2024)
- [Conditional computation in neural networks: principles and research trends](https://mlsanity.com/paper/2403.07965/) (2024)
- [NACHOS: Neural Architecture Search for Hardware Constrained Early Exit Neural Networks](https://mlsanity.com/paper/2401.13330/) (2024)
- [SECS: Efficient Deep Stream Processing via Class Skew Dichotomy](https://mlsanity.com/paper/1809.06691/) (2018)
- [Embedded CNN based vehicle classification and counting in non-laned road traffic](https://mlsanity.com/paper/1901.06358/) (2019)

## Abstract (arXiv)

Deep neural networks (DNNs) are widely used for their ability to model complex patterns across domains such as computer vision, speech recognition, and robotics. However, larger models, while often more accurate, are computationally expensive and energy-intensive. Since such a cost is typically needed only for challenging inputs, dynamically selecting lighter models for simpler inputs can improve efficiency with minimal impact on accuracy. We introduce PERTINENCE, a runtime method that selects, from a set of pre-trained models, the lightest model likely to process each input correctly. An ML-based dispatcher performs this selection, and a genetic algorithm explores dispatcher training strategies to identify Pareto-optimal trade-offs between accuracy and computational cost. We evaluate PERTINENCE on CNNs trained on CIFAR-10 and CIFAR-100, ViTs trained on TinyImageNet, and a YOLO-based road occupancy estimation application using real-time intersection camera feeds. Results show that PERTINENCE matches or improves the accuracy of state-of-the-art pre-trained models while reducing operations by up to 36%, with equivalent or lower end-to-end inference time through tunable invocation intervals.