# Light-Weight RefineNet for Real-Time Semantic Segmentation

arXiv: https://arxiv.org/abs/1810.03272 · HTML: https://mlsanity.com/paper/1810.03272/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Oct 2018.

## Built on by (most cited first, 27 of 27)

- [Dynamic Multimodal Fusion](https://mlsanity.com/paper/2204.00102/) (2022)
- [UniRestore: Unified Perceptual and Task-Oriented Image Restoration Model Using Diffusion Prior](https://mlsanity.com/paper/2501.13134/) (2025)
- [Geometry-Guided Street-View Panorama Synthesis from Satellite Imagery](https://mlsanity.com/paper/2103.01623/) (2021)
- [E2Style: Improve the Efficiency and Effectiveness of StyleGAN Inversion](https://mlsanity.com/paper/2104.07661/) (2021)
- [FIFO: Learning Fog-invariant Features for Foggy Scene Segmentation](https://mlsanity.com/paper/2204.01587/) (2022)
- [AsymFormer: Asymmetrical Cross-Modal Representation Learning for Mobile Platform Real-Time RGB-D Semantic Segmentation](https://mlsanity.com/paper/2309.14065/) (2023)
- [Revisiting Crowd Counting: State-of-the-art, Trends, and Future Perspectives](https://mlsanity.com/paper/2209.07271/) (2022)
- [To Adapt or Not to Adapt? Real-Time Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2307.15063/) (2023)
- [Efficient Global-Local Memory for Real-time Instrument Segmentation of Robotic Surgical Video](https://mlsanity.com/paper/2109.13593/) (2021)
- [Feature Enhancer Segmentation Network (FES-Net) for Vessel Segmentation](https://mlsanity.com/paper/2309.03535/) (2023)
- [Exposing Semantic Segmentation Failures via Maximum Discrepancy Competition](https://mlsanity.com/paper/2103.00259/) (2021)
- [On Efficient Real-Time Semantic Segmentation: A Survey](https://mlsanity.com/paper/2206.08605/) (2022)
- [Semantic Library Adaptation: LoRA Retrieval and Fusion for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2503.21780/) (2025)
- [Single-Stage 3D Geometry-Preserving Depth Estimation Model Training on Dataset Mixtures with Uncalibrated Stereo Data](https://mlsanity.com/paper/2306.02878/) (2023)
- [Multitask Network for Joint Object Detection, Semantic Segmentation and Human Pose Estimation in Vehicle Occupancy Monitoring](https://mlsanity.com/paper/2205.01515/) (2022)
- [Perception Framework through Real-Time Semantic Segmentation and Scene Recognition on a Wearable System for the Visually Impaired](https://mlsanity.com/paper/2103.04136/) (2021)
- [Deep Multi-Branch Aggregation Network for Real-Time Semantic Segmentation in Street Scenes](https://mlsanity.com/paper/2203.04037/) (2022)
- [GAM-Depth: Self-Supervised Indoor Depth Estimation Leveraging a Gradient-Aware Mask and Semantic Constraints](https://mlsanity.com/paper/2402.14354/) (2024)
- [A Novel 3D-UNet Deep Learning Framework Based on High-Dimensional Bilateral Grid for Edge Consistent Single Image Depth Estimation](https://mlsanity.com/paper/2105.10129/) (2021)
- [CI-Net: Contextual Information for Joint Semantic Segmentation and Depth Estimation](https://mlsanity.com/paper/2107.13800/) (2021)
- [Temporal Fusion Based Mutli-scale Semantic Segmentation for Detecting Concealed Baggage Threats](https://mlsanity.com/paper/2111.02651/) (2021)
- [LDMRes-Net: Enabling Efficient Medical Image Segmentation on IoT and Edge Platforms](https://mlsanity.com/paper/2306.06145/) (2023)
- [Use square root affinity to regress labels in semantic segmentation](https://mlsanity.com/paper/2103.04990/) (2021)
- [Issues in Object Detection in Videos using Common Single-Image CNNs](https://mlsanity.com/paper/2105.12822/) (2021)
- [Spatio-Temporal Dual-Stream Neural Network for Sequential Whole-Body PET Segmentation](https://mlsanity.com/paper/2106.04961/) (2021)
- [Density-based clustering with fully-convolutional networks for crowd flow detection from drones](https://mlsanity.com/paper/2301.04937/) (2023)
- [ConceptVAE: Self-Supervised Fine-Grained Concept Disentanglement from 2D Echocardiographies](https://mlsanity.com/paper/2502.01335/) (2025)

## Abstract (arXiv)

We consider an important task of effective and efficient semantic image segmentation. In particular, we adapt a powerful semantic segmentation architecture, called RefineNet, into the more compact one, suitable even for tasks requiring real-time performance on high-resolution inputs. To this end, we identify computationally expensive blocks in the original setup, and propose two modifications aimed to decrease the number of parameters and floating point operations. By doing that, we achieve more than twofold model reduction, while keeping the performance levels almost intact. Our fastest model undergoes a significant speed-up boost from 20 FPS to 55 FPS on a generic GPU card on 512x512 inputs with solid 81.1% mean iou performance on the test set of PASCAL VOC, while our slowest model with 32 FPS (from original 17 FPS) shows 82.7% mean iou on the same dataset. Alternatively, we showcase that our approach is easily mixable with light-weight classification networks: we attain 79.2% mean iou on PASCAL VOC using a model that contains only 3.3M parameters and performs only 9.3B floating point operations.