# F2Net: A Frequency-Fused Network for Ultra-High Resolution Remote Sensing Segmentation

arXiv: https://arxiv.org/abs/2506.07847 · HTML: https://mlsanity.com/paper/2506.07847/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 33 references that are in the map.
- First posted on arXiv 9 Jun 2025.

## Builds on (most cited first, 15 of 15)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Segmenter: Transformer for Semantic Segmentation](https://mlsanity.com/paper/2105.05633/) (2021)
- [PointRend: Image Segmentation as Rendering](https://mlsanity.com/paper/1912.08193/) (2019)
- [DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Images](https://mlsanity.com/paper/1805.06561/) (2018)
- [ICNet for Real-Time Semantic Segmentation on High-Resolution Images](https://mlsanity.com/paper/1704.08545/) (2017)
- [TinyViT: Fast Pretraining Distillation for Small Vision Transformers](https://mlsanity.com/paper/2207.10666/) (2022)
- [Attention to Scale: Scale-aware Semantic Image Segmentation](https://mlsanity.com/paper/1511.03339/) (2015)
- [Rethinking BiSeNet For Real-time Semantic Segmentation](https://mlsanity.com/paper/2104.13188/) (2021)
- [CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinement](https://mlsanity.com/paper/2005.02551/) (2020)
- [Collaborative Global-Local Networks for Memory-Efficient Segmentation of Ultra-High Resolution Images](https://mlsanity.com/paper/1905.06368/) (2019)
- [Progressive Semantic Segmentation](https://mlsanity.com/paper/2104.03778/) (2021)
- [Towards Efficient and Scale-Robust Ultra-High-Definition Image Demoireing](https://mlsanity.com/paper/2207.09935/) (2022)
- [SFFNet: A Wavelet-Based Spatial and Frequency Domain Fusion Network for Remote Sensing Segmentation](https://mlsanity.com/paper/2405.01992/) (2024)

## Built on by (most cited first, 4 of 4)

- [GDGS: 3D Gaussian Splatting Via Geometry-Guided Initialization And Dynamic Density Control](https://mlsanity.com/paper/2507.00363/) (2025)
- [WeaveEarth: Structured Evidence Construction and Reasoning for Training-Free UHR Remote Sensing Understanding](https://mlsanity.com/paper/2607.10120/) (2026)
- [A Global-Local Cross-Attention Network for Ultra-high Resolution Remote Sensing Image Semantic Segmentation](https://mlsanity.com/paper/2506.19406/) (2025)
- [A Spatial-Spectral-Frequency Interactive Network for Multimodal Remote Sensing Classification](https://mlsanity.com/paper/2510.04628/) (2025)

## Abstract (arXiv)

Semantic segmentation of ultra-high-resolution (UHR) remote sensing imagery is critical for applications like environmental monitoring and urban planning but faces computational and optimization challenges. Conventional methods either lose fine details through downsampling or fragment global context via patch processing. While multi-branch networks address this trade-off, they suffer from computational inefficiency and conflicting gradient dynamics during training. We propose F2Net, a frequency-aware framework that decomposes UHR images into high- and low-frequency components for specialized processing. The high-frequency branch preserves full-resolution structural details, while the low-frequency branch processes downsampled inputs through dual sub-branches capturing short- and long-range dependencies. A Hybrid-Frequency Fusion module integrates these observations, guided by two novel objectives: Cross-Frequency Alignment Loss ensures semantic consistency between frequency components, and Cross-Frequency Balance Loss regulates gradient magnitudes across branches to stabilize training. Evaluated on DeepGlobe and Inria Aerial benchmarks, F2Net achieves state-of-the-art performance with mIoU of 80.22 and 83.39, respectively. Our code will be publicly available.