# Adaptative Inference Cost With Convolutional Neural Mixture Models

arXiv: https://arxiv.org/abs/1908.06694 · HTML: https://mlsanity.com/paper/1908.06694/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Aug 2019.

## Built on by (most cited first, 5 of 5)

- [Glance and Focus Networks for Dynamic Visual Recognition](https://mlsanity.com/paper/2201.03014/) (2022)
- [EBJR: Energy-Based Joint Reasoning for Adaptive Inference](https://mlsanity.com/paper/2110.10343/) (2021)
- [A Survey of Historical Learning: Learning Models with Learning History](https://mlsanity.com/paper/2303.12992/) (2023)
- [ItNet: iterative neural networks with small graphs for accurate, efficient and anytime semantic segmentation](https://mlsanity.com/paper/2101.08685/) (2021)
- [Exploring Budgeted Image Classification with Content-Sensitive Resource Allocation](https://mlsanity.com/paper/2607.23997/) (2026)

## Abstract (arXiv)

Despite the outstanding performance of convolutional neural networks (CNNs) for many vision tasks, the required computational cost during inference is problematic when resources are limited. In this context, we propose Convolutional Neural Mixture Models (CNMMs), a probabilistic model embedding a large number of CNNs that can be jointly trained and evaluated in an efficient manner. Within the proposed framework, we present different mechanisms to prune subsets of CNNs from the mixture, allowing to easily adapt the computational cost required for inference. Image classification and semantic segmentation experiments show that our method achieve excellent accuracy-compute trade-offs. Moreover, unlike most of previous approaches, a single CNMM provides a large range of operating points along this trade-off, without any re-training.