# E2CM: Early Exit via Class Means for Efficient Supervised and Unsupervised Learning

arXiv: https://arxiv.org/abs/2103.01148 · HTML: https://mlsanity.com/paper/2103.01148/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 42 references that are in the map.
- First posted on arXiv 1 Mar 2021.

## Builds on (most cited first, 30 of 30)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Learning to Compare: Relation Network for Few-Shot Learning](https://mlsanity.com/paper/1711.06025/) (2017)
- [Unsupervised Deep Embedding for Clustering Analysis](https://mlsanity.com/paper/1511.06335/) (2015)
- [Prevalence of Neural Collapse during the terminal phase of deep learning training](https://mlsanity.com/paper/2008.08186/) (2020)
- [A Closer Look at Few-shot Classification](https://mlsanity.com/paper/1904.04232/) (2019)
- [BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks](https://mlsanity.com/paper/1709.01686/) (2017)
- [Deep Learning for Classical Japanese Literature](https://mlsanity.com/paper/1812.01718/) (2018)
- [SkipNet: Learning Dynamic Routing in Convolutional Networks](https://mlsanity.com/paper/1711.09485/) (2017)
- [DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference](https://mlsanity.com/paper/2004.12993/) (2020)
- [BERT Loses Patience: Fast and Robust Inference with Early Exit](https://mlsanity.com/paper/2006.04152/) (2020)
- [Quantized Convolutional Neural Networks for Mobile Devices](https://mlsanity.com/paper/1512.06473/) (2015)
- [Conditional Computation in Neural Networks for faster models](https://mlsanity.com/paper/1511.06297/) (2015)
- [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)
- [Resolution Adaptive Networks for Efficient Inference](https://mlsanity.com/paper/2003.07326/) (2020)
- [Transferrable Prototypical Networks for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1904.11227/) (2019)
- [Conditional Deep Learning for Energy-Efficient and Enhanced Pattern Recognition](https://mlsanity.com/paper/1509.08971/) (2015)
- [Deciding How to Decide: Dynamic Routing in Artificial Neural Networks](https://mlsanity.com/paper/1703.06217/) (2017)
- [Separation and Concentration in Deep Networks](https://mlsanity.com/paper/2012.10424/) (2020)

## Built on by (most cited first, 8 of 8)

- [Federated Momentum Contrastive Clustering](https://mlsanity.com/paper/2206.05093/) (2022)
- [On the Opportunities of Green Computing: A Survey](https://mlsanity.com/paper/2311.00447/) (2023)
- [Class Based Thresholding in Early Exit Semantic Segmentation Networks](https://mlsanity.com/paper/2210.15621/) (2022)
- [Pruning Early Exit Networks](https://mlsanity.com/paper/2207.03644/) (2022)
- [Optimization of Layer Skipping and Frequency Scaling for Convolutional Neural Networks under Latency Constraint](https://mlsanity.com/paper/2503.24014/) (2025)
- [When Do Early-Exit Networks Generalize? A PAC-Bayesian Theory of Adaptive Depth](https://mlsanity.com/paper/2604.15764/) (2026)
- [Adaptive AI: Energy Efficient Multi-exit TinyML on Intelligent Vision Systems at the Edge](https://mlsanity.com/paper/2609.11939/) (2026)
- [Theoretical Guarantees for One-Shot Magnitude Pruning and Compute-Adaptive Early Exit](https://mlsanity.com/paper/2609.12337/) (2026)

## Abstract (arXiv)

State-of-the-art neural networks with early exit mechanisms often need considerable amount of training and fine tuning to achieve good performance with low computational cost. We propose a novel early exit technique, Early Exit Class Means (E2CM), based on class means of samples. Unlike most existing schemes, E2CM does not require gradient-based training of internal classifiers and it does not modify the base network by any means. This makes it particularly useful for neural network training in low-power devices, as in wireless edge networks. We evaluate the performance and overheads of E2CM over various base neural networks such as MobileNetV3, EfficientNet, ResNet, and datasets such as CIFAR-100, ImageNet, and KMNIST. Our results show that, given a fixed training time budget, E2CM achieves higher accuracy as compared to existing early exit mechanisms. Moreover, if there are no limitations on the training time budget, E2CM can be combined with an existing early exit scheme to boost the latter's performance, achieving a better trade-off between computational cost and network accuracy. We also show that E2CM can be used to decrease the computational cost in unsupervised learning tasks.