# DCNAS: Densely Connected Neural Architecture Search for Semantic Image Segmentation

arXiv: https://arxiv.org/abs/2003.11883 · HTML: https://mlsanity.com/paper/2003.11883/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Mar 2020.

## Built on by (most cited first, 30 of 33)

- [Neural Architecture Search for Spiking Neural Networks](https://mlsanity.com/paper/2201.10355/) (2022)
- [AutoSNN: Towards Energy-Efficient Spiking Neural Networks](https://mlsanity.com/paper/2201.12738/) (2022)
- [HR-NAS: Searching Efficient High-Resolution Neural Architectures with Lightweight Transformers](https://mlsanity.com/paper/2106.06560/) (2021)
- [Loss Functions in the Era of Semantic Segmentation: A Survey and Outlook](https://mlsanity.com/paper/2312.05391/) (2023)
- [Semantic Segmentation In-the-Wild Without Seeing Any Segmentation Examples](https://mlsanity.com/paper/2112.03185/) (2021)
- [FBNetV5: Neural Architecture Search for Multiple Tasks in One Run](https://mlsanity.com/paper/2111.10007/) (2021)
- [Neural Architecture Search for Dense Prediction Tasks in Computer Vision](https://mlsanity.com/paper/2202.07242/) (2022)
- [CountFormer: Multi-View Crowd Counting Transformer](https://mlsanity.com/paper/2407.02047/) (2024)
- [Urban Scene Semantic Segmentation with Low-Cost Coarse Annotation](https://mlsanity.com/paper/2212.07911/) (2022)
- [RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks](https://mlsanity.com/paper/2206.06637/) (2022)
- [Convolutional Embedding Makes Hierarchical Vision Transformer Stronger](https://mlsanity.com/paper/2207.13317/) (2022)
- [Learning Versatile Neural Architectures by Propagating Network Codes](https://mlsanity.com/paper/2103.13253/) (2021)
- [Exploring the Intersection between Neural Architecture Search and Continual Learning](https://mlsanity.com/paper/2206.05625/) (2022)
- [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)
- [Transferable Attack for Semantic Segmentation](https://mlsanity.com/paper/2307.16572/) (2023)
- [Hidden Path Selection Network for Semantic Segmentation of Remote Sensing Images](https://mlsanity.com/paper/2112.05220/) (2021)
- [Adaptive Cross-Layer Attention for Image Restoration](https://mlsanity.com/paper/2203.03619/) (2022)
- [Multi-Prior Learning via Neural Architecture Search for Blind Face Restoration](https://mlsanity.com/paper/2206.13962/) (2022)
- [DCLP: Neural Architecture Predictor with Curriculum Contrastive Learning](https://mlsanity.com/paper/2302.13020/) (2023)
- [Revisiting Multi-Scale Feature Fusion for Semantic Segmentation](https://mlsanity.com/paper/2203.12683/) (2022)
- [Latent Graph Attention for Enhanced Spatial Context](https://mlsanity.com/paper/2307.04149/) (2023)
- [Few-Shot Fruit Segmentation via Transfer Learning](https://mlsanity.com/paper/2405.02556/) (2024)
- [Implantable Adaptive Cells: A Novel Enhancement for Pre-Trained U-Nets in Medical Image Segmentation](https://mlsanity.com/paper/2405.03420/) (2024)
- [LightSNN: Lightweight Architecture Search for Sparse and Accurate Spiking Neural Networks](https://mlsanity.com/paper/2503.21846/) (2025)
- [TSLA: A Task-Specific Learning Adaptation for Semantic Segmentation on Autonomous Vehicles Platform](https://mlsanity.com/paper/2508.12279/) (2025)
- [NAS-based Recursive Stage Partial Network (RSPNet) for Light-Weight Semantic Segmentation](https://mlsanity.com/paper/2210.00698/) (2022)
- [SSHNN: Semi-Supervised Hybrid NAS Network for Echocardiographic Image Segmentation](https://mlsanity.com/paper/2309.04672/) (2023)
- [An Approach for Efficient Neural Architecture Search Space Definition](https://mlsanity.com/paper/2310.17669/) (2023)
- [NAS-ASDet: An Adaptive Design Method for Surface Defect Detection Network using Neural Architecture Search](https://mlsanity.com/paper/2311.10952/) (2023)

## Abstract (arXiv)

Neural Architecture Search (NAS) has shown great potentials in automatically designing scalable network architectures for dense image predictions. However, existing NAS algorithms usually compromise on restricted search space and search on proxy task to meet the achievable computational demands. To allow as wide as possible network architectures and avoid the gap between target and proxy dataset, we propose a Densely Connected NAS (DCNAS) framework, which directly searches the optimal network structures for the multi-scale representations of visual information, over a large-scale target dataset. Specifically, by connecting cells with each other using learnable weights, we introduce a densely connected search space to cover an abundance of mainstream network designs. Moreover, by combining both path-level and channel-level sampling strategies, we design a fusion module to reduce the memory consumption of ample search space. We demonstrate that the architecture obtained from our DCNAS algorithm achieves state-of-the-art performances on public semantic image segmentation benchmarks, including 84.3% on Cityscapes, and 86.9% on PASCAL VOC 2012. We also retain leading performances when evaluating the architecture on the more challenging ADE20K and Pascal Context dataset.