DIS2: Disentanglement Meets Distillation with Classwise Attention for Robust Remote Sensing Segmentation under Missing Modalities

TL;DR

DIS2 introduces a novel framework combining disentanglement and knowledge distillation with classwise attention to improve remote sensing segmentation when some data modalities are missing, addressing heterogeneity and scale variation.

Contribution

The paper presents DIS2, a new paradigm that actively compensates for missing information and incorporates class-specific modality contributions for robust remote sensing segmentation.

Findings

Significantly outperforms existing methods on multiple benchmarks.

Effectively handles missing modalities in heterogeneous remote sensing data.

Improves segmentation accuracy with classwise feature learning.

Abstract

The efficacy of multimodal learning in remote sensing (RS) is severely undermined by missing modalities. The challenge is exacerbated by the RS highly heterogeneous data and huge scale variation. Consequently, paradigms proven effective in other domains often fail when confronted with these unique data characteristics. Conventional disentanglement learning, which relies on significant feature overlap between modalities (modality-invariant), is insufficient for this heterogeneity. Similarly, knowledge distillation becomes an ill-posed mimicry task where a student fails to focus on the necessary compensatory knowledge, leaving the semantic gap unaddressed. Our work is therefore built upon three pillars uniquely designed for RS: (1) principled missing information compensation, (2) class-specific modality contribution, and (3) multi-resolution feature importance. We propose a novel method DIS2, a new paradigm shifting from modality-shared feature dependence and untargeted imitation to active, guided missing features compensation. Its core novelty lies in a reformulated synergy between disentanglement learning and knowledge distillation, termed DLKD. Compensatory features are explicitly captured which, when fused with the features of the available modality, approximate the ideal fused representation of the full-modality case. To address the class-specific challenge, our Classwise Feature Learning Module (CFLM) adaptively learn discriminative evidence for each target depending on signal availability. Both DLKD and CFLM are supported by a hierarchical hybrid fusion (HF) structure using features across resolutions to strengthen prediction. Extensive experiments validate that our proposed approach significantly outperforms state-of-the-art methods across benchmarks.