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

TL;DR

F2Net introduces a frequency-aware segmentation framework for ultra-high-resolution remote sensing images, effectively preserving details and global context, leading to state-of-the-art results on benchmark datasets.

Contribution

The paper presents a novel frequency decomposition approach with specialized branches and fusion modules, improving UHR image segmentation accuracy and training stability.

Findings

Achieves state-of-the-art mIoU of 80.22 on DeepGlobe

Achieves state-of-the-art mIoU of 83.39 on Inria Aerial

Demonstrates effective preservation of details and context in segmentation

Abstract

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.