# Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cells

arXiv: https://arxiv.org/abs/1810.10804 · HTML: https://mlsanity.com/paper/1810.10804/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Oct 2018.

## Built on by (most cited first, 30 of 39)

- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Rethinking Semantic Segmentation: A Prototype View](https://mlsanity.com/paper/2203.15102/) (2022)
- [Neural Architecture Search: Insights from 1000 Papers](https://mlsanity.com/paper/2301.08727/) (2023)
- [TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation](https://mlsanity.com/paper/2204.05525/) (2022)
- [A Comprehensive Survey on Hardware-Aware Neural Architecture Search](https://mlsanity.com/paper/2101.09336/) (2021)
- [HR-NAS: Searching Efficient High-Resolution Neural Architectures with Lightweight Transformers](https://mlsanity.com/paper/2106.06560/) (2021)
- [StructToken : Rethinking Semantic Segmentation with Structural Prior](https://mlsanity.com/paper/2203.12612/) (2022)
- [AdvRush: Searching for Adversarially Robust Neural Architectures](https://mlsanity.com/paper/2108.01289/) (2021)
- [Core-set Sampling for Efficient Neural Architecture Search](https://mlsanity.com/paper/2107.06869/) (2021)
- [Rethinking Neural Operations for Diverse Tasks](https://mlsanity.com/paper/2103.15798/) (2021)
- [Multi-Exit Semantic Segmentation Networks](https://mlsanity.com/paper/2106.03527/) (2021)
- [LOGICSEG: Parsing Visual Semantics with Neural Logic Learning and Reasoning](https://mlsanity.com/paper/2309.13556/) (2023)
- [Generic Neural Architecture Search via Regression](https://mlsanity.com/paper/2108.01899/) (2021)
- [Semantic Segmentation by Early Region Proxy](https://mlsanity.com/paper/2203.14043/) (2022)
- [GI-NAS: Boosting Gradient Inversion Attacks Through Adaptive Neural Architecture Search](https://mlsanity.com/paper/2405.20725/) (2024)
- [Neural Architecture Search for Dense Prediction Tasks in Computer Vision](https://mlsanity.com/paper/2202.07242/) (2022)
- [SFNet: Faster and Accurate Semantic Segmentation via Semantic Flow](https://mlsanity.com/paper/2207.04415/) (2022)
- [Learning Versatile Neural Architectures by Propagating Network Codes](https://mlsanity.com/paper/2103.13253/) (2021)
- [DHA: End-to-End Joint Optimization of Data Augmentation Policy, Hyper-parameter and Architecture](https://mlsanity.com/paper/2109.05765/) (2021)
- [NAS-FCOS: Efficient Search for Object Detection Architectures](https://mlsanity.com/paper/2110.12423/) (2021)
- [Improving Quantization-aware Training of Low-Precision Network via Block Replacement on Full-Precision Counterpart](https://mlsanity.com/paper/2412.15846/) (2024)
- [SDTP: Semantic-aware Decoupled Transformer Pyramid for Dense Image Prediction](https://mlsanity.com/paper/2109.08963/) (2021)
- [Surrogate-assisted Multi-objective Neural Architecture Search for Real-time Semantic Segmentation](https://mlsanity.com/paper/2208.06820/) (2022)
- [Bag of Tricks for Neural Architecture Search](https://mlsanity.com/paper/2107.03719/) (2021)
- [CHASE: Robust Visual Tracking via Cell-Level Differentiable Neural Architecture Search](https://mlsanity.com/paper/2107.03463/) (2021)
- [EASNet: Searching Elastic and Accurate Network Architecture for Stereo Matching](https://mlsanity.com/paper/2207.09796/) (2022)
- [Efficient Heterogeneous Video Segmentation at the Edge](https://mlsanity.com/paper/2208.11666/) (2022)
- [A Pairwise Comparison Relation-assisted Multi-objective Evolutionary Neural Architecture Search Method with Multi-population Mechanism](https://mlsanity.com/paper/2407.15600/) (2024)
- [Learning Morphisms with Gauss-Newton Approximation for Growing Networks](https://mlsanity.com/paper/2411.05855/) (2024)
- [LoMix: Learnable Weighted Multi-Scale Logits Mixing for Medical Image Segmentation](https://mlsanity.com/paper/2510.22995/) (2025)

## Abstract (arXiv)

Automated design of neural network architectures tailored for a specific task is an extremely promising, albeit inherently difficult, avenue to explore. While most results in this domain have been achieved on image classification and language modelling problems, here we concentrate on dense per-pixel tasks, in particular, semantic image segmentation using fully convolutional networks. In contrast to the aforementioned areas, the design choices of a fully convolutional network require several changes, ranging from the sort of operations that need to be used---e.g., dilated convolutions---to a solving of a more difficult optimisation problem. In this work, we are particularly interested in searching for high-performance compact segmentation architectures, able to run in real-time using limited resources. To achieve that, we intentionally over-parameterise the architecture during the training time via a set of auxiliary cells that provide an intermediate supervisory signal and can be omitted during the evaluation phase. The design of the auxiliary cell is emitted by a controller, a neural network with the fixed structure trained using reinforcement learning. More crucially, we demonstrate how to efficiently search for these architectures within limited time and computational budgets. In particular, we rely on a progressive strategy that terminates non-promising architectures from being further trained, and on Polyak averaging coupled with knowledge distillation to speed-up the convergence. Quantitatively, in 8 GPU-days our approach discovers a set of architectures performing on-par with state-of-the-art among compact models on the semantic segmentation, pose estimation and depth prediction tasks. Code will be made available here: https://github.com/drsleep/nas-segm-pytorch