# Exploring Budgeted Image Classification with Content-Sensitive Resource Allocation

arXiv: https://arxiv.org/abs/2607.23997 · HTML: https://mlsanity.com/paper/2607.23997/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 31 references that are in the map.
- First posted on arXiv 27 Jul 2026.

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

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Energy and Policy Considerations for Deep Learning in NLP](https://mlsanity.com/paper/1906.02243/) (2019)
- [EfficientNetV2: Smaller Models and Faster Training](https://mlsanity.com/paper/2104.00298/) (2021)
- [BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks](https://mlsanity.com/paper/1709.01686/) (2017)
- [Adaptive Computation Time for Recurrent Neural Networks](https://mlsanity.com/paper/1603.08983/) (2016)
- [Functional Map of the World](https://mlsanity.com/paper/1711.07846/) (2017)
- [SkipNet: Learning Dynamic Routing in Convolutional Networks](https://mlsanity.com/paper/1711.09485/) (2017)
- [Slimmable Neural Networks](https://mlsanity.com/paper/1812.08928/) (2018)
- [Adaptive Neural Networks for Efficient Inference](https://mlsanity.com/paper/1702.07811/) (2017)
- [Revisiting ResNets: Improved Training and Scaling Strategies](https://mlsanity.com/paper/2103.07579/) (2021)
- [Convolutional Networks with Adaptive Inference Graphs](https://mlsanity.com/paper/1711.11503/) (2017)
- [Resolution Adaptive Networks for Efficient Inference](https://mlsanity.com/paper/2003.07326/) (2020)
- [Dynamic Channel Pruning: Feature Boosting and Suppression](https://mlsanity.com/paper/1810.05331/) (2018)
- [Spatially Adaptive Computation Time for Residual Networks](https://mlsanity.com/paper/1612.02297/) (2016)
- [Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image Classification](https://mlsanity.com/paper/2010.05300/) (2020)
- [Dynamic Convolutions: Exploiting Spatial Sparsity for Faster Inference](https://mlsanity.com/paper/1912.03203/) (2019)
- [Improved Techniques for Training Adaptive Deep Networks](https://mlsanity.com/paper/1908.06294/) (2019)
- [Dynamic Computational Time for Visual Attention](https://mlsanity.com/paper/1703.10332/) (2017)
- [Hard-Attention for Scalable Image Classification](https://mlsanity.com/paper/2102.10212/) (2021)
- [Changing Model Behavior at Test-Time Using Reinforcement Learning](https://mlsanity.com/paper/1702.07780/) (2017)
- [Adaptative Inference Cost With Convolutional Neural Mixture Models](https://mlsanity.com/paper/1908.06694/) (2019)

## Abstract (arXiv)

The ever-growing adoption of Artificial Intelligence (AI) creates the need to deploy Deep Neural Networks in a variety of computational environments. We consider dynamic environments, where computational requirements are subject to change, and we pose the following question: How do we adjust the complexity of an AI classification system, in order to maximize its accuracy, while meeting changing computational constraints? We call this problem Budgeted Image Classification, and we formally formulate it as a resource allocation integer program. Given a computational budget, a batch of images, and a classification system that can make decisions with varying complexity (it has multiple decision points), we explore strategies to allocate images to decision points, in order to maximize accuracy within the available budget. The original integer program is NP-Hard, so, we propose a continuous relaxation, leading to a content-agnostic allocation strategy which assigns images to decision points without considering their particular content. We address this issue by proposing a content-sensitive strategy, that we experimentally show it leads to superior performance. We theoretically study the behavior of our strategies, deriving conditions that must be satisfied by decision points to be suitable for budgeted classification. We analyze fails cases, offering insights for future research directions.