# FasterSeg: Searching for Faster Real-time Semantic Segmentation

arXiv: https://arxiv.org/abs/1912.10917 · HTML: https://mlsanity.com/paper/1912.10917/

## Key facts

- Cited by 73 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Dec 2019.

## Built on by (most cited first, 30 of 73)

- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective](https://mlsanity.com/paper/2102.11535/) (2021)
- [Rethinking Semantic Segmentation: A Prototype View](https://mlsanity.com/paper/2203.15102/) (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)
- [PIDNet: A Real-time Semantic Segmentation Network Inspired by PID Controllers](https://mlsanity.com/paper/2206.02066/) (2022)
- [TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation](https://mlsanity.com/paper/2204.05525/) (2022)
- [OpenEarthMap: A Benchmark Dataset for Global High-Resolution Land Cover Mapping](https://mlsanity.com/paper/2210.10732/) (2022)
- [Neural Feature Search for RGB-Infrared Person Re-Identification](https://mlsanity.com/paper/2104.02366/) (2021)
- [DiNTS: Differentiable Neural Network Topology Search for 3D Medical Image Segmentation](https://mlsanity.com/paper/2103.15954/) (2021)
- [PP-LiteSeg: A Superior Real-Time Semantic Segmentation Model](https://mlsanity.com/paper/2204.02681/) (2022)
- [RTFormer: Efficient Design for Real-Time Semantic Segmentation with Transformer](https://mlsanity.com/paper/2210.07124/) (2022)
- [Smart at what cost? Characterising Mobile Deep Neural Networks in the wild](https://mlsanity.com/paper/2109.13963/) (2021)
- [PSViT: Better Vision Transformer via Token Pooling and Attention Sharing](https://mlsanity.com/paper/2108.03428/) (2021)
- [Zero-Shot Neural Architecture Search: Challenges, Solutions, and Opportunities](https://mlsanity.com/paper/2307.01998/) (2023)
- [LOGICSEG: Parsing Visual Semantics with Neural Logic Learning and Reasoning](https://mlsanity.com/paper/2309.13556/) (2023)
- [FBNetV5: Neural Architecture Search for Multiple Tasks in One Run](https://mlsanity.com/paper/2111.10007/) (2021)
- [GhostNets on Heterogeneous Devices via Cheap Operations](https://mlsanity.com/paper/2201.03297/) (2022)
- [FAKD: Feature Augmented Knowledge Distillation for Semantic Segmentation](https://mlsanity.com/paper/2208.14143/) (2022)
- [Computation-efficient Deep Learning for Computer Vision: A Survey](https://mlsanity.com/paper/2308.13998/) (2023)
- [Neural Architecture Search for Dense Prediction Tasks in Computer Vision](https://mlsanity.com/paper/2202.07242/) (2022)
- [Gait Recognition in the Wild: A Large-scale Benchmark and NAS-based Baseline](https://mlsanity.com/paper/2205.02692/) (2022)
- [Delta Distillation for Efficient Video Processing](https://mlsanity.com/paper/2203.09594/) (2022)
- [Efficient Joint-Dimensional Search with Solution Space Regularization for Real-Time Semantic Segmentation](https://mlsanity.com/paper/2208.05271/) (2022)
- [Self-supervised Hypergraphs for Learning Multiple World Interpretations](https://mlsanity.com/paper/2308.07615/) (2023)
- [Exposing Semantic Segmentation Failures via Maximum Discrepancy Competition](https://mlsanity.com/paper/2103.00259/) (2021)
- [Lightweight Monocular Depth with a Novel Neural Architecture Search Method](https://mlsanity.com/paper/2108.11105/) (2021)
- [Semantic Scene Segmentation for Robotics Applications](https://mlsanity.com/paper/2108.11128/) (2021)
- [Understanding and Accelerating Neural Architecture Search with Training-Free and Theory-Grounded Metrics](https://mlsanity.com/paper/2108.11939/) (2021)

## Abstract (arXiv)

We present FasterSeg, an automatically designed semantic segmentation network with not only state-of-the-art performance but also faster speed than current methods. Utilizing neural architecture search (NAS), FasterSeg is discovered from a novel and broader search space integrating multi-resolution branches, that has been recently found to be vital in manually designed segmentation models. To better calibrate the balance between the goals of high accuracy and low latency, we propose a decoupled and fine-grained latency regularization, that effectively overcomes our observed phenomenons that the searched networks are prone to "collapsing" to low-latency yet poor-accuracy models. Moreover, we seamlessly extend FasterSeg to a new collaborative search (co-searching) framework, simultaneously searching for a teacher and a student network in the same single run. The teacher-student distillation further boosts the student model's accuracy. Experiments on popular segmentation benchmarks demonstrate the competency of FasterSeg. For example, FasterSeg can run over 30% faster than the closest manually designed competitor on Cityscapes, while maintaining comparable accuracy.