mlsanityData to 7 Oct 2026

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

arXiv 2303.16322 ↗First posted 28 Mar 2023cs.CV cs.AIcited by 0

Not on the map. Why?

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 22 of its 31 references that are in the map. First posted on arXiv 28 Mar 2023.

Builds on

22 of 31 references.

References · 22

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  3. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  4. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  5. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  6. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,320
  7. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  8. 2018Efficient Neural Architecture Search via Parameter Sharingcited by 831
  9. 2019Once-for-All: Train One Network and Specialize it for Efficient Deploymentcited by 778
  10. 2019Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentationcited by 258
  11. 2018Searching for Efficient Multi-Scale Architectures for Dense Image Predictioncited by 96
  12. 2018Recent progress in semantic image segmentationcited by 39
10 more
  1. 2018Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cellscited by 39
  2. 2019SqueezeNAS: Fast neural architecture search for faster semantic segmentationcited by 31
  3. 2021ECG-TCN: Wearable Cardiac Arrhythmia Detection with a Temporal Convolutional Networkcited by 14
  4. 2019Resource Optimized Neural Architecture Search for 3D Medical Image Segmentationcited by 13
  5. 2021Sound Event Detection with Binary Neural Networks on Tightly Power-Constrained IoT Devicescited by 10
  6. 2022GVSoC: A Highly Configurable, Fast and Accurate Full-Platform Simulator for RISC-V based IoT Processorscited by 6
  7. 2019Architecture Search of Dynamic Cells for Semantic Video Segmentationcited by 5
  8. 2019Self-Adaptive 2D-3D Ensemble of Fully Convolutional Networks for Medical Image Segmentationcited by 4
  9. 2021AttendSeg: A Tiny Attention Condenser Neural Network for Semantic Segmentation on the Edgecited by 4
  10. 2019Template-Based Automatic Search of Compact Semantic Segmentation Architecturescited by 2

Built on by

Not cited yet.