# Multi-Exit Semantic Segmentation Networks

arXiv: https://arxiv.org/abs/2106.03527 · HTML: https://mlsanity.com/paper/2106.03527/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 59 of its 79 references that are in the map.
- First posted on arXiv 7 Jun 2021.

## Builds on (most cited first, 30 of 59)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation](https://mlsanity.com/paper/1511.00561/) (2015)
- [Multi-Scale Context Aggregation by Dilated Convolutions](https://mlsanity.com/paper/1511.07122/) (2015)
- [BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation](https://mlsanity.com/paper/1808.00897/) (2018)
- [ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/1811.12833/) (2018)
- [BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks](https://mlsanity.com/paper/1709.01686/) (2017)
- [Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation](https://mlsanity.com/paper/1905.08094/) (2019)
- [RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation](https://mlsanity.com/paper/1611.06612/) (2016)
- [Learning Deconvolution Network for Semantic Segmentation](https://mlsanity.com/paper/1505.04366/) (2015)
- [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)
- [Dilated Residual Networks](https://mlsanity.com/paper/1705.09914/) (2017)
- [Structured Knowledge Distillation for Dense Prediction](https://mlsanity.com/paper/1903.04197/) (2019)
- [ICNet for Real-Time Semantic Segmentation on High-Resolution Images](https://mlsanity.com/paper/1704.08545/) (2017)
- [Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation](https://mlsanity.com/paper/1901.02985/) (2019)
- [Edge Intelligence: Paving the Last Mile of Artificial Intelligence with Edge Computing](https://mlsanity.com/paper/1905.10083/) (2019)
- [Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Network](https://mlsanity.com/paper/1703.02719/) (2017)
- [BlockDrop: Dynamic Inference Paths in Residual Networks](https://mlsanity.com/paper/1711.08393/) (2017)

## Built on by (most cited first, 18 of 18)

- [Adaptive Inference through Early-Exit Networks: Design, Challenges and Directions](https://mlsanity.com/paper/2106.05022/) (2021)
- [Path Independent Equilibrium Models Can Better Exploit Test-Time Computation](https://mlsanity.com/paper/2211.09961/) (2022)
- [Auditing Membership Leakages of Multi-Exit Networks](https://mlsanity.com/paper/2208.11180/) (2022)
- [Fixing Overconfidence in Dynamic Neural Networks](https://mlsanity.com/paper/2302.06359/) (2023)
- [Window-Based Early-Exit Cascades for Uncertainty Estimation: When Deep Ensembles are More Efficient than Single Models](https://mlsanity.com/paper/2303.08010/) (2023)
- [The Future of Consumer Edge-AI Computing](https://mlsanity.com/paper/2210.10514/) (2022)
- [Conditional computation in neural networks: principles and research trends](https://mlsanity.com/paper/2403.07965/) (2024)
- [OODIn: An Optimised On-Device Inference Framework for Heterogeneous Mobile Devices](https://mlsanity.com/paper/2106.04723/) (2021)
- [Fluid Batching: Exit-Aware Preemptive Serving of Early-Exit Neural Networks on Edge NPUs](https://mlsanity.com/paper/2209.13443/) (2022)
- [Class Based Thresholding in Early Exit Semantic Segmentation Networks](https://mlsanity.com/paper/2210.15621/) (2022)
- [A Survey on Dynamic Neural Networks: from Computer Vision to Multi-modal Sensor Fusion](https://mlsanity.com/paper/2501.07451/) (2025)
- [SlimSeg: Slimmable Semantic Segmentation with Boundary Supervision](https://mlsanity.com/paper/2207.06242/) (2022)
- [ATHEENA: A Toolflow for Hardware Early-Exit Network Automation](https://mlsanity.com/paper/2304.08400/) (2023)
- [NEO-KD: Knowledge-Distillation-Based Adversarial Training for Robust Multi-Exit Neural Networks](https://mlsanity.com/paper/2311.00428/) (2023)
- [How to Reach Real-Time AI on Consumer Devices? Solutions for Programmable and Custom Architectures](https://mlsanity.com/paper/2106.15021/) (2021)
- [LAECIPS: Large Vision Model Assisted Adaptive Edge-Cloud Collaboration for IoT-based Embodied Intelligence System](https://mlsanity.com/paper/2404.10498/) (2024)
- [A Model Stealing Attack Against Multi-Exit Networks](https://mlsanity.com/paper/2305.13584/) (2023)
- [Efficient Deep Learning for Biometrics: Overview, Challenges and Trends in Ear of Frugal AI](https://mlsanity.com/paper/2602.08809/) (2026)

## Abstract (arXiv)

Semantic segmentation arises as the backbone of many vision systems, spanning from self-driving cars and robot navigation to augmented reality and teleconferencing. Frequently operating under stringent latency constraints within a limited resource envelope, optimising for efficient execution becomes important. At the same time, the heterogeneous capabilities of the target platforms and the diverse constraints of different applications require the design and training of multiple target-specific segmentation models, leading to excessive maintenance costs. To this end, we propose a framework for converting state-of-the-art segmentation CNNs to Multi-Exit Semantic Segmentation (MESS) networks: specially trained models that employ parametrised early exits along their depth to i) dynamically save computation during inference on easier samples and ii) save training and maintenance cost by offering a post-training customisable speed-accuracy trade-off. Designing and training such networks naively can hurt performance. Thus, we propose a novel two-staged training scheme for multi-exit networks. Furthermore, the parametrisation of MESS enables co-optimising the number, placement and architecture of the attached segmentation heads along with the exit policy, upon deployment via exhaustive search in <1 GPUh. This allows MESS to rapidly adapt to the device capabilities and application requirements for each target use-case, offering a train-once-deploy-everywhere solution. MESS variants achieve latency gains of up to 2.83x with the same accuracy, or 5.33 pp higher accuracy for the same computational budget, compared to the original backbone network. Lastly, MESS delivers orders of magnitude faster architectural customisation, compared to state-of-the-art techniques.