# Early-exit Convolutional Neural Networks

arXiv: https://arxiv.org/abs/2409.05336 · HTML: https://mlsanity.com/paper/2409.05336/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 22 references that are in the map.
- First posted on arXiv 9 Sep 2024.

## Builds on (most cited first, 12 of 12)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks](https://mlsanity.com/paper/1709.01686/) (2017)
- [SkipNet: Learning Dynamic Routing in Convolutional Networks](https://mlsanity.com/paper/1711.09485/) (2017)
- [BlockDrop: Dynamic Inference Paths in Residual Networks](https://mlsanity.com/paper/1711.08393/) (2017)
- [Adaptive Neural Networks for Efficient Inference](https://mlsanity.com/paper/1702.07811/) (2017)
- [Convolutional Networks with Adaptive Inference Graphs](https://mlsanity.com/paper/1711.11503/) (2017)
- [Spatially Adaptive Computation Time for Residual Networks](https://mlsanity.com/paper/1612.02297/) (2016)
- [Channel Gating Neural Networks](https://mlsanity.com/paper/1805.12549/) (2018)
- [Conditional Deep Learning for Energy-Efficient and Enhanced Pattern Recognition](https://mlsanity.com/paper/1509.08971/) (2015)
- [Adaptive Neural Trees](https://mlsanity.com/paper/1807.06699/) (2018)
- [Dynamically Sacrificing Accuracy for Reduced Computation: Cascaded Inference Based on Softmax Confidence](https://mlsanity.com/paper/1805.10982/) (2018)

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

- [PTEENet: Post-Trained Early-Exit Neural Networks Augmentation for Inference Cost Optimization](https://mlsanity.com/paper/2501.02508/) (2025)
- [Decoupled Multi-Predictor Optimization for Inference-Efficient Model Tuning](https://mlsanity.com/paper/2511.03245/) (2025)
- [RAViT: Resolution-Adaptive Vision Transformer](https://mlsanity.com/paper/2602.24159/) (2026)

## Abstract (arXiv)

This paper is aimed at developing a method that reduces the computational cost of convolutional neural networks (CNN) during inference. Conventionally, the input data pass through a fixed neural network architecture. However, easy examples can be classified at early stages of processing and conventional networks do not take this into account. In this paper, we introduce 'Early-exit CNNs', EENets for short, which adapt their computational cost based on the input by stopping the inference process at certain exit locations. In EENets, there are a number of exit blocks each of which consists of a confidence branch and a softmax branch. The confidence branch computes the confidence score of exiting (i.e. stopping the inference process) at that location; while the softmax branch outputs a classification probability vector. Both branches are learnable and their parameters are separate. During training of EENets, in addition to the classical classification loss, the computational cost of inference is taken into account as well. As a result, the network adapts its many confidence branches to the inputs so that less computation is spent for easy examples. Inference works as in conventional feed-forward networks, however, when the output of a confidence branch is larger than a certain threshold, the inference stops for that specific example. The idea of EENets is applicable to available CNN architectures such as ResNets. Through comprehensive experiments on MNIST, SVHN, CIFAR10 and Tiny-ImageNet datasets, we show that early-exit (EE) ResNets achieve similar accuracy with their non-EE versions while reducing the computational cost to 20% of the original. Code is available at https://github.com/eksuas/eenets.pytorch