# Searching for Efficient Multi-Scale Architectures for Dense Image Prediction

arXiv: https://arxiv.org/abs/1809.04184 · HTML: https://mlsanity.com/paper/1809.04184/

## Key facts

- Cited by 96 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Sep 2018.

## Built on by (most cited first, 30 of 96)

- [Coordinate Attention for Efficient Mobile Network Design](https://mlsanity.com/paper/2103.02907/) (2021)
- [Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective](https://mlsanity.com/paper/2102.11535/) (2021)
- [VOLO: Vision Outlooker for Visual Recognition](https://mlsanity.com/paper/2106.13112/) (2021)
- [HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation](https://mlsanity.com/paper/2204.13132/) (2022)
- [Neural Architecture Search: Insights from 1000 Papers](https://mlsanity.com/paper/2301.08727/) (2023)
- [EfficientLPS: Efficient LiDAR Panoptic Segmentation](https://mlsanity.com/paper/2102.08009/) (2021)
- [TransNAS-Bench-101: Improving Transferability and Generalizability of Cross-Task Neural Architecture Search](https://mlsanity.com/paper/2105.11871/) (2021)
- [AutoCTS: Automated Correlated Time Series Forecasting -- Extended Version](https://mlsanity.com/paper/2112.11174/) (2021)
- [HR-NAS: Searching Efficient High-Resolution Neural Architectures with Lightweight Transformers](https://mlsanity.com/paper/2106.06560/) (2021)
- [Amodal Panoptic Segmentation](https://mlsanity.com/paper/2202.11542/) (2022)
- [Peekaboo: Text to Image Diffusion Models are Zero-Shot Segmentors](https://mlsanity.com/paper/2211.13224/) (2022)
- [Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications](https://mlsanity.com/paper/2204.11786/) (2022)
- [Towards Improving the Consistency, Efficiency, and Flexibility of Differentiable Neural Architecture Search](https://mlsanity.com/paper/2101.11342/) (2021)
- [CDGNet: Class Distribution Guided Network for Human Parsing](https://mlsanity.com/paper/2111.14173/) (2021)
- [Learning Deep Multimodal Feature Representation with Asymmetric Multi-layer Fusion](https://mlsanity.com/paper/2108.05009/) (2021)
- [RoI Tanh-polar Transformer Network for Face Parsing in the Wild](https://mlsanity.com/paper/2102.02717/) (2021)
- [Joint-DetNAS: Upgrade Your Detector with NAS, Pruning and Dynamic Distillation](https://mlsanity.com/paper/2105.12971/) (2021)
- [Scaling Laws Under the Microscope: Predicting Transformer Performance from Small Scale Experiments](https://mlsanity.com/paper/2202.06387/) (2022)
- [BN-NAS: Neural Architecture Search with Batch Normalization](https://mlsanity.com/paper/2108.07375/) (2021)
- [Perceiving the Invisible: Proposal-Free Amodal Panoptic Segmentation](https://mlsanity.com/paper/2205.14637/) (2022)
- [Multi-Exit Semantic Segmentation Networks](https://mlsanity.com/paper/2106.03527/) (2021)
- [Efficient Architecture Search for Diverse Tasks](https://mlsanity.com/paper/2204.07554/) (2022)
- [Open Source Vizier: Distributed Infrastructure and API for Reliable and Flexible Blackbox Optimization](https://mlsanity.com/paper/2207.13676/) (2022)
- [AutoReCon: Neural Architecture Search-based Reconstruction for Data-free Compression](https://mlsanity.com/paper/2105.12151/) (2021)
- [Uncertainty-aware Panoptic Segmentation](https://mlsanity.com/paper/2206.14554/) (2022)
- [AmodalSynthDrive: A Synthetic Amodal Perception Dataset for Autonomous Driving](https://mlsanity.com/paper/2309.06547/) (2023)
- [Classification of Long Sequential Data using Circular Dilated Convolutional Neural Networks](https://mlsanity.com/paper/2201.02143/) (2022)
- [Neural Architecture Search for Dense Prediction Tasks in Computer Vision](https://mlsanity.com/paper/2202.07242/) (2022)
- [FADNet++: Real-Time and Accurate Disparity Estimation with Configurable Networks](https://mlsanity.com/paper/2110.02582/) (2021)
- [T-AutoML: Automated Machine Learning for Lesion Segmentation using Transformers in 3D Medical Imaging](https://mlsanity.com/paper/2111.07535/) (2021)

## Abstract (arXiv)

The design of neural network architectures is an important component for achieving state-of-the-art performance with machine learning systems across a broad array of tasks. Much work has endeavored to design and build architectures automatically through clever construction of a search space paired with simple learning algorithms. Recent progress has demonstrated that such meta-learning methods may exceed scalable human-invented architectures on image classification tasks. An open question is the degree to which such methods may generalize to new domains. In this work we explore the construction of meta-learning techniques for dense image prediction focused on the tasks of scene parsing, person-part segmentation, and semantic image segmentation. Constructing viable search spaces in this domain is challenging because of the multi-scale representation of visual information and the necessity to operate on high resolution imagery. Based on a survey of techniques in dense image prediction, we construct a recursive search space and demonstrate that even with efficient random search, we can identify architectures that outperform human-invented architectures and achieve state-of-the-art performance on three dense prediction tasks including 82.7% on Cityscapes (street scene parsing), 71.3% on PASCAL-Person-Part (person-part segmentation), and 87.9% on PASCAL VOC 2012 (semantic image segmentation). Additionally, the resulting architecture is more computationally efficient, requiring half the parameters and half the computational cost as previous state of the art systems.