# DifferSeg: Towards Diverse Multimodal Binary Segmentation via Differential Perception and Frequency Guidance

Source: [DifferSeg: Towards Diverse Multimodal Binary Segmentation via Differential Perception and Frequency Guidance](<https://www.sota2.com/research/paper/6a279e7890966ade919bfb8c>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-10T05:01:35.776Z

Authors: Qiangqiang Zhou, Jiawei Xu, Yong Chen, Dandan Zhu, Yugen Yi, Xiaoqi Zhao

Published: 2026-06-08T01:10:36.000Z

## Abstract

In many binary segmentation tasks, most multimodal methods rely on fixed feature concatenation for cross-modal interaction and straightforward decoder designs dominated by low-frequency semantics. %ToDO: % However, they ignore two key challenges: one is the lack of an adaptive mechanism to handle modality discrepancies and complementarity, and the other is the absence of an efficient decoding strategy to balance both high- and low-frequency representations. % In this work, we propose a simple yet general multimodal binary segmentation framework, termed DifferSeg, to address both problems simultaneously. With the help of the differential perception fusion (DPF) module, DifferSeg employs learnable differential operators to adaptively align multimodal features and enhance their complementarity through residual fusion, effectively mitigating modality mismatch and fusion redundancy. % In addition, we design a frequency-guided decoder (FGD) that builds cross-frequency interactions and multi-path upsampling to maintain consistency between detailed high-frequency structures and semantic low-frequency representations, ensuring fine-grained boundary recovery and noise suppression. % Benefiting from these designs, DifferSeg can be easily generalized to diverse binary segmentation tasks, including both natural and medical modalities. Without bells and whistles, it consistently surpasses 67 state-of-the-art methods across 29 public datasets involving 18 downstream tasks, demonstrating superior generalization and segmentation accuracy.Code and pretrained models will be available at the Link.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Salient Object Detection on ORSSD](<https://www.sota2.com/research/sota/salient-object-detection-on-orssd.md>): Salient Object Detection; ORSSD; P(F\_beta): 0.9322.

- [Salient Object Detection on EORSSD](<https://www.sota2.com/research/sota/salient-object-detection-on-eorssd.md>): Salient Object Detection; EORSSD; P(F\_beta): not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2606.08906>)

[PDF](<https://arxiv.org/pdf/2606.08906.pdf>)
