# FMAS: Fast Multi-Objective SuperNet Architecture Search for Semantic Segmentation

arXiv: https://arxiv.org/abs/2303.16322 · HTML: https://mlsanity.com/paper/2303.16322/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 31 references that are in the map.
- First posted on arXiv 28 Mar 2023.

## Builds on (most cited first, 22 of 22)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [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)
- [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)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Efficient Neural Architecture Search via Parameter Sharing](https://mlsanity.com/paper/1802.03268/) (2018)
- [Once-for-All: Train One Network and Specialize it for Efficient Deployment](https://mlsanity.com/paper/1908.09791/) (2019)
- [Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation](https://mlsanity.com/paper/1901.02985/) (2019)
- [Searching for Efficient Multi-Scale Architectures for Dense Image Prediction](https://mlsanity.com/paper/1809.04184/) (2018)
- [Recent progress in semantic image segmentation](https://mlsanity.com/paper/1809.10198/) (2018)
- [Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cells](https://mlsanity.com/paper/1810.10804/) (2018)
- [SqueezeNAS: Fast neural architecture search for faster semantic segmentation](https://mlsanity.com/paper/1908.01748/) (2019)
- [ECG-TCN: Wearable Cardiac Arrhythmia Detection with a Temporal Convolutional Network](https://mlsanity.com/paper/2103.13740/) (2021)
- [Resource Optimized Neural Architecture Search for 3D Medical Image Segmentation](https://mlsanity.com/paper/1909.00548/) (2019)
- [Sound Event Detection with Binary Neural Networks on Tightly Power-Constrained IoT Devices](https://mlsanity.com/paper/2101.04446/) (2021)
- [GVSoC: A Highly Configurable, Fast and Accurate Full-Platform Simulator for RISC-V based IoT Processors](https://mlsanity.com/paper/2201.08166/) (2022)
- [Architecture Search of Dynamic Cells for Semantic Video Segmentation](https://mlsanity.com/paper/1904.02371/) (2019)
- [Self-Adaptive 2D-3D Ensemble of Fully Convolutional Networks for Medical Image Segmentation](https://mlsanity.com/paper/1907.11587/) (2019)
- [AttendSeg: A Tiny Attention Condenser Neural Network for Semantic Segmentation on the Edge](https://mlsanity.com/paper/2104.14623/) (2021)
- [Template-Based Automatic Search of Compact Semantic Segmentation Architectures](https://mlsanity.com/paper/1904.02365/) (2019)

## Abstract (arXiv)

We present FMAS, a fast multi-objective neural architecture search framework for semantic segmentation. FMAS subsamples the structure and pre-trained parameters of DeepLabV3+, without fine-tuning, dramatically reducing training time during search. To further reduce candidate evaluation time, we use a subset of the validation dataset during the search. Only the final, Pareto non-dominated, candidates are ultimately fine-tuned using the complete training set. We evaluate FMAS by searching for models that effectively trade accuracy and computational cost on the PASCAL VOC 2012 dataset. FMAS finds competitive designs quickly, e.g., taking just 0.5 GPU days to discover a DeepLabV3+ variant that reduces FLOPs and parameters by 10% and 20% respectively, for less than 3% increased error. We also search on an edge device called GAP8 and use its latency as the metric. FMAS is capable of finding 2.2× faster network with 7.61% MIoU loss.