# ExFuse: Enhancing Feature Fusion for Semantic Segmentation

arXiv: https://arxiv.org/abs/1804.03821 · HTML: https://mlsanity.com/paper/1804.03821/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Apr 2018.

## Built on by (most cited first, 30 of 42)

- [Full-Duplex Strategy for Video Object Segmentation](https://mlsanity.com/paper/2108.03151/) (2021)
- [Frequency-aware Feature Fusion for Dense Image Prediction](https://mlsanity.com/paper/2408.12879/) (2024)
- [Unmasking Anomalies in Road-Scene Segmentation](https://mlsanity.com/paper/2307.13316/) (2023)
- [Uncertainty-aware Contrastive Distillation for Incremental Semantic Segmentation](https://mlsanity.com/paper/2203.14098/) (2022)
- [TRACER: Extreme Attention Guided Salient Object Tracing Network](https://mlsanity.com/paper/2112.07380/) (2021)
- [Looking Outside the Window: Wide-Context Transformer for the Semantic Segmentation of High-Resolution Remote Sensing Images](https://mlsanity.com/paper/2106.15754/) (2021)
- [GraphFPN: Graph Feature Pyramid Network for Object Detection](https://mlsanity.com/paper/2108.00580/) (2021)
- [Image Data Augmentation Approaches: A Comprehensive Survey and Future directions](https://mlsanity.com/paper/2301.02830/) (2023)
- [Frequency Dynamic Convolution for Dense Image Prediction](https://mlsanity.com/paper/2503.18783/) (2025)
- [Continual Attentive Fusion for Incremental Learning in Semantic Segmentation](https://mlsanity.com/paper/2202.00432/) (2022)
- [Detecting Anomalies in Semantic Segmentation with Prototypes](https://mlsanity.com/paper/2106.00472/) (2021)
- [Tilted Cross Entropy (TCE): Promoting Fairness in Semantic Segmentation](https://mlsanity.com/paper/2103.14051/) (2021)
- [Gated Multi-Resolution Transfer Network for Burst Restoration and Enhancement](https://mlsanity.com/paper/2304.06703/) (2023)
- [AutoGPart: Intermediate Supervision Search for Generalizable 3D Part Segmentation](https://mlsanity.com/paper/2203.06558/) (2022)
- [FLOAT: Factorized Learning of Object Attributes for Improved Multi-object Multi-part Scene Parsing](https://mlsanity.com/paper/2203.16168/) (2022)
- [Global Aggregation then Local Distribution for Scene Parsing](https://mlsanity.com/paper/2107.13154/) (2021)
- [Early Preparation Pays Off: New Classifier Pre-tuning for Class Incremental Semantic Segmentation](https://mlsanity.com/paper/2407.14142/) (2024)
- [Adapting Segment Anything Model to Multi-modal Salient Object Detection with Semantic Feature Fusion Guidance](https://mlsanity.com/paper/2408.15063/) (2024)
- [Learning Global-aware Kernel for Image Harmonization](https://mlsanity.com/paper/2305.11676/) (2023)
- [ALPS: An Auto-Labeling and Pre-training Scheme for Remote Sensing Segmentation With Segment Anything Model](https://mlsanity.com/paper/2406.10855/) (2024)
- [Hybrid Skip: A Biologically Inspired Skip Connection for the UNet Architecture](https://mlsanity.com/paper/2207.04721/) (2022)
- [U-HRNet: Delving into Improving Semantic Representation of High Resolution Network for Dense Prediction](https://mlsanity.com/paper/2210.07140/) (2022)
- [Coupling Global Context and Local Contents for Weakly-Supervised Semantic Segmentation](https://mlsanity.com/paper/2304.09059/) (2023)
- [PathFL: Multi-Alignment Federated Learning for Pathology Image Segmentation](https://mlsanity.com/paper/2505.22522/) (2025)
- [Modeling the Background for Incremental and Weakly-Supervised Semantic Segmentation](https://mlsanity.com/paper/2201.13338/) (2022)
- [MMFL-Net: Multi-scale and Multi-granularity Feature Learning for Cross-domain Fashion Retrieval](https://mlsanity.com/paper/2210.15128/) (2022)
- [EFCNet: Every Feature Counts for Small Medical Object Segmentation](https://mlsanity.com/paper/2406.18201/) (2024)
- [Training-Free Point Cloud Recognition Based on Geometric and Semantic Information Fusion](https://mlsanity.com/paper/2409.04760/) (2024)
- [Dilated SpineNet for Semantic Segmentation](https://mlsanity.com/paper/2103.12270/) (2021)
- [Delving into Transformer for Incremental Semantic Segmentation](https://mlsanity.com/paper/2211.10253/) (2022)

## Abstract (arXiv)

Modern semantic segmentation frameworks usually combine low-level and high-level features from pre-trained backbone convolutional models to boost performance. In this paper, we first point out that a simple fusion of low-level and high-level features could be less effective because of the gap in semantic levels and spatial resolution. We find that introducing semantic information into low-level features and high-resolution details into high-level features is more effective for the later fusion. Based on this observation, we propose a new framework, named ExFuse, to bridge the gap between low-level and high-level features thus significantly improve the segmentation quality by 4.0% in total. Furthermore, we evaluate our approach on the challenging PASCAL VOC 2012 segmentation benchmark and achieve 87.9% mean IoU, which outperforms the previous state-of-the-art results.