# RGPNet: A Real-Time General Purpose Semantic Segmentation

arXiv: https://arxiv.org/abs/1912.01394 · HTML: https://mlsanity.com/paper/1912.01394/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Dec 2019.

## Built on by (most cited first, 9 of 9)

- [Highlighting the Importance of Reducing Research Bias and Carbon Emissions in CNNs](https://mlsanity.com/paper/2106.03242/) (2021)
- [On Efficient Real-Time Semantic Segmentation: A Survey](https://mlsanity.com/paper/2206.08605/) (2022)
- [Flying Guide Dog: Walkable Path Discovery for the Visually Impaired Utilizing Drones and Transformer-based Semantic Segmentation](https://mlsanity.com/paper/2108.07007/) (2021)
- [COVID-19 identification from volumetric chest CT scans using a progressively resized 3D-CNN incorporating segmentation, augmentation, and class-rebalancing](https://mlsanity.com/paper/2102.06169/) (2021)
- [AI Driven Road Maintenance Inspection](https://mlsanity.com/paper/2106.02567/) (2021)
- [CSRNet: Cascaded Selective Resolution Network for Real-time Semantic Segmentation](https://mlsanity.com/paper/2106.04400/) (2021)
- [Hierarchical Graph Pattern Understanding for Zero-Shot VOS](https://mlsanity.com/paper/2312.09525/) (2023)
- [AI-Driven Road Maintenance Inspection v2: Reducing Data Dependency & Quantifying Road Damage](https://mlsanity.com/paper/2210.03570/) (2022)
- [Progressive Growing of Patch Size: Curriculum Learning for Accelerated and Improved Medical Image Segmentation](https://mlsanity.com/paper/2510.23241/) (2025)

## Abstract (arXiv)

We propose a real-time general purpose semantic segmentation architecture, RGPNet, which achieves significant performance gain in complex environments. RGPNet consists of a light-weight asymmetric encoder-decoder and an adaptor. The adaptor helps preserve and refine the abstract concepts from multiple levels of distributed representations between the encoder and decoder. It also facilitates the gradient flow from deeper layers to shallower layers. Our experiments demonstrate that RGPNet can generate segmentation results in real-time with comparable accuracy to the state-of-the-art non-real-time heavy models. Moreover, towards green AI, we show that using an optimized label-relaxation technique with progressive resizing can reduce the training time by up to 60% while preserving the performance. We conclude that RGPNet obtains a better speed-accuracy trade-off across multiple datasets.