# FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation

arXiv: https://arxiv.org/abs/1903.11816 · HTML: https://mlsanity.com/paper/1903.11816/

## Key facts

- Cited by 70 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Mar 2019.

## Built on by (most cited first, 30 of 70)

- [UIU-Net: U-Net in U-Net for Infrared Small Object Detection](https://mlsanity.com/paper/2212.00968/) (2022)
- [Vision-Language Models for Medical Report Generation and Visual Question Answering: A Review](https://mlsanity.com/paper/2403.02469/) (2024)
- [Cross-City Matters: A Multimodal Remote Sensing Benchmark Dataset for Cross-City Semantic Segmentation using High-Resolution Domain Adaptation Networks](https://mlsanity.com/paper/2309.16499/) (2023)
- [GANav: Efficient Terrain Segmentation for Robot Navigation in Unstructured Outdoor Environments](https://mlsanity.com/paper/2103.04233/) (2021)
- [CTNet: Context-based Tandem Network for Semantic Segmentation](https://mlsanity.com/paper/2104.09805/) (2021)
- [Mining Unseen Classes via Regional Objectness: A Simple Baseline for Incremental Segmentation](https://mlsanity.com/paper/2211.06866/) (2022)
- [Semantic Segmentation in Art Paintings](https://mlsanity.com/paper/2203.03238/) (2022)
- [Cerberus Transformer: Joint Semantic, Affordance and Attribute Parsing](https://mlsanity.com/paper/2111.12608/) (2021)
- [Multi-Exit Semantic Segmentation Networks](https://mlsanity.com/paper/2106.03527/) (2021)
- [AUCSeg: AUC-oriented Pixel-level Long-tail Semantic Segmentation](https://mlsanity.com/paper/2409.20398/) (2024)
- [Domain Adaptation Meets Zero-Shot Learning: An Annotation-Efficient Approach to Multi-Modality Medical Image Segmentation](https://mlsanity.com/paper/2203.10332/) (2022)
- [Customize Segment Anything Model for Multi-Modal Semantic Segmentation with Mixture of LoRA Experts](https://mlsanity.com/paper/2412.04220/) (2024)
- [CAR: Class-aware Regularizations for Semantic Segmentation](https://mlsanity.com/paper/2203.07160/) (2022)
- [AutoMMLab: Automatically Generating Deployable Models from Language Instructions for Computer Vision Tasks](https://mlsanity.com/paper/2402.15351/) (2024)
- [MMSFormer: Multimodal Transformer for Material and Semantic Segmentation](https://mlsanity.com/paper/2309.04001/) (2023)
- [A Pixel-Level Meta-Learner for Weakly Supervised Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2111.01418/) (2021)
- [CaveSeg: Deep Semantic Segmentation and Scene Parsing for Autonomous Underwater Cave Exploration](https://mlsanity.com/paper/2309.11038/) (2023)
- [Semantic Aware Diffusion Inverse Tone Mapping](https://mlsanity.com/paper/2405.15468/) (2024)
- [Understanding Spatio-Temporal Relations in Human-Object Interaction using Pyramid Graph Convolutional Network](https://mlsanity.com/paper/2410.07912/) (2024)
- [Towards Complex Backgrounds: A Unified Difference-Aware Decoder for Binary Segmentation](https://mlsanity.com/paper/2210.15156/) (2022)
- [Benchmarking Segmentation Models with Mask-Preserved Attribute Editing](https://mlsanity.com/paper/2403.01231/) (2024)
- [Deep Image Matting with Flexible Guidance Input](https://mlsanity.com/paper/2110.10898/) (2021)
- [MSCDA: Multi-level Semantic-guided Contrast Improves Unsupervised Domain Adaptation for Breast MRI Segmentation in Small Datasets](https://mlsanity.com/paper/2301.02554/) (2023)
- [UDTIRI: An Online Open-Source Intelligent Road Inspection Benchmark Suite](https://mlsanity.com/paper/2304.08842/) (2023)
- [SSSegmenation: An Open Source Supervised Semantic Segmentation Toolbox Based on PyTorch](https://mlsanity.com/paper/2305.17091/) (2023)
- [CADSpotting: Robust Panoptic Symbol Spotting on Large-Scale CAD Drawings](https://mlsanity.com/paper/2412.07377/) (2024)
- [MSE Loss with Outlying Label for Imbalanced Classification](https://mlsanity.com/paper/2107.02393/) (2021)
- [DPF: Learning Dense Prediction Fields with Weak Supervision](https://mlsanity.com/paper/2303.16890/) (2023)
- [SU-SAM: A Simple Unified Framework for Adapting Segment Anything Model in Underperformed Scenes](https://mlsanity.com/paper/2401.17803/) (2024)
- [Sparse Refinement for Efficient High-Resolution Semantic Segmentation](https://mlsanity.com/paper/2407.19014/) (2024)

## Abstract (arXiv)

Modern approaches for semantic segmentation usually employ dilated convolutions in the backbone to extract high-resolution feature maps, which brings heavy computation complexity and memory footprint. To replace the time and memory consuming dilated convolutions, we propose a novel joint upsampling module named Joint Pyramid Upsampling (JPU) by formulating the task of extracting high-resolution feature maps into a joint upsampling problem. With the proposed JPU, our method reduces the computation complexity by more than three times without performance loss. Experiments show that JPU is superior to other upsampling modules, which can be plugged into many existing approaches to reduce computation complexity and improve performance. By replacing dilated convolutions with the proposed JPU module, our method achieves the state-of-the-art performance in Pascal Context dataset (mIoU of 53.13%) and ADE20K dataset (final score of 0.5584) while running 3 times faster.