# Customizable Architecture Search for Semantic Segmentation

arXiv: https://arxiv.org/abs/1908.09550 · HTML: https://mlsanity.com/paper/1908.09550/

## Key facts

- Cited by 41 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Aug 2019.

## Built on by (most cited first, 30 of 41)

- [HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation](https://mlsanity.com/paper/2204.13132/) (2022)
- [Rethinking BiSeNet For Real-time Semantic Segmentation](https://mlsanity.com/paper/2104.13188/) (2021)
- [Lite-HRNet: A Lightweight High-Resolution Network](https://mlsanity.com/paper/2104.06403/) (2021)
- [Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes](https://mlsanity.com/paper/2101.06085/) (2021)
- [AlphaNet: Improved Training of Supernets with Alpha-Divergence](https://mlsanity.com/paper/2102.07954/) (2021)
- [RTFormer: Efficient Design for Real-Time Semantic Segmentation with Transformer](https://mlsanity.com/paper/2210.07124/) (2022)
- [AdvRush: Searching for Adversarially Robust Neural Architectures](https://mlsanity.com/paper/2108.01289/) (2021)
- [WAS-VTON: Warping Architecture Search for Virtual Try-on Network](https://mlsanity.com/paper/2108.00386/) (2021)
- [AttaNet: Attention-Augmented Network for Fast and Accurate Scene Parsing](https://mlsanity.com/paper/2103.05930/) (2021)
- [Generalization Properties of NAS under Activation and Skip Connection Search](https://mlsanity.com/paper/2209.07238/) (2022)
- [Neural Architecture Search for Dense Prediction Tasks in Computer Vision](https://mlsanity.com/paper/2202.07242/) (2022)
- [Rethinking Dilated Convolution for Real-time Semantic Segmentation](https://mlsanity.com/paper/2111.09957/) (2021)
- [Gait Recognition in the Wild: A Large-scale Benchmark and NAS-based Baseline](https://mlsanity.com/paper/2205.02692/) (2022)
- [SFNet: Faster and Accurate Semantic Segmentation via Semantic Flow](https://mlsanity.com/paper/2207.04415/) (2022)
- [Efficient Joint-Dimensional Search with Solution Space Regularization for Real-Time Semantic Segmentation](https://mlsanity.com/paper/2208.05271/) (2022)
- [Fast and Accurate Scene Parsing via Bi-direction Alignment Networks](https://mlsanity.com/paper/2105.11651/) (2021)
- [Surrogate-assisted Multi-objective Neural Architecture Search for Real-time Semantic Segmentation](https://mlsanity.com/paper/2208.06820/) (2022)
- [MixSearch: Searching for Domain Generalized Medical Image Segmentation Architectures](https://mlsanity.com/paper/2102.13280/) (2021)
- [SlimSeg: Slimmable Semantic Segmentation with Boundary Supervision](https://mlsanity.com/paper/2207.06242/) (2022)
- [Lightweight and Progressively-Scalable Networks for Semantic Segmentation](https://mlsanity.com/paper/2207.13600/) (2022)
- [Multi-scale Evolutionary Neural Architecture Search for Deep Spiking Neural Networks](https://mlsanity.com/paper/2304.10749/) (2023)
- [Domain Generalization with Pseudo-Domain Label for Face Anti-Spoofing](https://mlsanity.com/paper/2107.06552/) (2021)
- [Towards Self-supervised and Weight-preserving Neural Architecture Search](https://mlsanity.com/paper/2206.04125/) (2022)
- [Cross-CBAM: A Lightweight network for Scene Segmentation](https://mlsanity.com/paper/2306.02306/) (2023)
- [AASeg: Attention Aware Network for Real Time Semantic Segmentation](https://mlsanity.com/paper/2108.04349/) (2021)
- [Aux-NAS: Exploiting Auxiliary Labels with Negligibly Extra Inference Cost](https://mlsanity.com/paper/2405.05695/) (2024)
- [TopoNAS: Boosting Search Efficiency of Gradient-based NAS via Topological Simplification](https://mlsanity.com/paper/2408.01311/) (2024)
- [Exploring Complicated Search Spaces with Interleaving-Free Sampling](https://mlsanity.com/paper/2112.02488/) (2021)
- [Technical Report on Subspace Pyramid Fusion Network for Semantic Segmentation](https://mlsanity.com/paper/2204.01278/) (2022)
- [FlowNAS: Neural Architecture Search for Optical Flow Estimation](https://mlsanity.com/paper/2207.01271/) (2022)

## Abstract (arXiv)

In this paper, we propose a Customizable Architecture Search (CAS) approach to automatically generate a network architecture for semantic image segmentation. The generated network consists of a sequence of stacked computation cells. A computation cell is represented as a directed acyclic graph, in which each node is a hidden representation (i.e., feature map) and each edge is associated with an operation (e.g., convolution and pooling), which transforms data to a new layer. During the training, the CAS algorithm explores the search space for an optimized computation cell to build a network. The cells of the same type share one architecture but with different weights. In real applications, however, an optimization may need to be conducted under some constraints such as GPU time and model size. To this end, a cost corresponding to the constraint will be assigned to each operation. When an operation is selected during the search, its associated cost will be added to the objective. As a result, our CAS is able to search an optimized architecture with customized constraints. The approach has been thoroughly evaluated on Cityscapes and CamVid datasets, and demonstrates superior performance over several state-of-the-art techniques. More remarkably, our CAS achieves 72.3% mIoU on the Cityscapes dataset with speed of 108 FPS on an Nvidia TitanXp GPU.