# Partial Order Pruning: for Best Speed/Accuracy Trade-off in Neural Architecture Search

arXiv: https://arxiv.org/abs/1903.03777 · HTML: https://mlsanity.com/paper/1903.03777/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Mar 2019.

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

- [SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation](https://mlsanity.com/paper/2209.08575/) (2022)
- [CLIP-Driven Universal Model for Organ Segmentation and Tumor Detection](https://mlsanity.com/paper/2301.00785/) (2023)
- [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)
- [PIDNet: A Real-time Semantic Segmentation Network Inspired by PID Controllers](https://mlsanity.com/paper/2206.02066/) (2022)
- [Zen-NAS: A Zero-Shot NAS for High-Performance Deep Image Recognition](https://mlsanity.com/paper/2102.01063/) (2021)
- [A Comprehensive Survey on Hardware-Aware Neural Architecture Search](https://mlsanity.com/paper/2101.09336/) (2021)
- [DiNTS: Differentiable Neural Network Topology Search for 3D Medical Image Segmentation](https://mlsanity.com/paper/2103.15954/) (2021)
- [Frequency-Adaptive Dilated Convolution for Semantic Segmentation](https://mlsanity.com/paper/2403.05369/) (2024)
- [RTFormer: Efficient Design for Real-Time Semantic Segmentation with Transformer](https://mlsanity.com/paper/2210.07124/) (2022)
- [Joint-DetNAS: Upgrade Your Detector with NAS, Pruning and Dynamic Distillation](https://mlsanity.com/paper/2105.12971/) (2021)
- [Searching for Fast Model Families on Datacenter Accelerators](https://mlsanity.com/paper/2102.05610/) (2021)
- [Robust Semantic Segmentation with Superpixel-Mix](https://mlsanity.com/paper/2108.00968/) (2021)
- [Stage-Aware Feature Alignment Network for Real-Time Semantic Segmentation of Street Scenes](https://mlsanity.com/paper/2203.04031/) (2022)
- [AttaNet: Attention-Augmented Network for Fast and Accurate Scene Parsing](https://mlsanity.com/paper/2103.05930/) (2021)
- [SFNet: Faster and Accurate Semantic Segmentation via Semantic Flow](https://mlsanity.com/paper/2207.04415/) (2022)
- [Efficient Semantic Segmentation by Altering Resolutions for Compressed Videos](https://mlsanity.com/paper/2303.07224/) (2023)
- [Learning Efficient, Explainable and Discriminative Representations for Pulmonary Nodules Classification](https://mlsanity.com/paper/2101.07429/) (2021)
- [On Efficient Real-Time Semantic Segmentation: A Survey](https://mlsanity.com/paper/2206.08605/) (2022)
- [Fast and Accurate Scene Parsing via Bi-direction Alignment Networks](https://mlsanity.com/paper/2105.11651/) (2021)
- [A Survey of Large-Scale Deep Learning Serving System Optimization: Challenges and Opportunities](https://mlsanity.com/paper/2111.14247/) (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)
- [Deep Common Feature Mining for Efficient Video Semantic Segmentation](https://mlsanity.com/paper/2403.02689/) (2024)
- [DWRSeg: Rethinking Efficient Acquisition of Multi-scale Contextual Information for Real-time Semantic Segmentation](https://mlsanity.com/paper/2212.01173/) (2022)
- [Multi-scale Evolutionary Neural Architecture Search for Deep Spiking Neural Networks](https://mlsanity.com/paper/2304.10749/) (2023)
- [CONet: Channel Optimization for Convolutional Neural Networks](https://mlsanity.com/paper/2108.06822/) (2021)
- [Revisiting Multi-Scale Feature Fusion for Semantic Segmentation](https://mlsanity.com/paper/2203.12683/) (2022)
- [MKANet: A Lightweight Network with Sobel Boundary Loss for Efficient Land-cover Classification of Satellite Remote Sensing Imagery](https://mlsanity.com/paper/2207.13866/) (2022)
- [ContextFormer: Redefining Efficiency in Semantic Segmentation](https://mlsanity.com/paper/2501.19255/) (2025)

## Abstract (arXiv)

Achieving good speed and accuracy trade-off on a target platform is very important in deploying deep neural networks in real world scenarios. However, most existing automatic architecture search approaches only concentrate on high performance. In this work, we propose an algorithm that can offer better speed/accuracy trade-off of searched networks, which is termed "Partial Order Pruning". It prunes the architecture search space with a partial order assumption to automatically search for the architectures with the best speed and accuracy trade-off. Our algorithm explicitly takes profile information about the inference speed on the target platform into consideration. With the proposed algorithm, we present several Dongfeng (DF) networks that provide high accuracy and fast inference speed on various application GPU platforms. By further searching decoder architectures, our DF-Seg real-time segmentation networks yield state-of-the-art speed/accuracy trade-off on both the target embedded device and the high-end GPU.