Unified architectures that jointly perform semantic segmentation and monocular height estimation offer improved computational efficiency through shared representations, but face challenges in remote sensing applications: scarce annotations, intertask interference, and cross-regional domain shifts. These issues often lead to severe performance degradation, as models struggle with domain discrepancies and conflicting gradients. Moreover, existing domain adaptation methods remain constrained, suffering from low pseudolabel confidence, feature misalignment, and negative transfer. To address these, we propose DPCDO, a dynamic-coordinated learning approach for unsupervised multitask domain adaptation, which jointly models the multivariate conditional generation process of task outputs, domain alignment, and pseudolabel consistency. DPCDO integrates three synergistic modules: 1) dynamic patchwise prototype matching dynamically aligns local feature distributions to accommodate topographic diversity, promoting domain-invariant representation learning and cross-task information sharing; 2) multistream multiscale consistency constraint performs multiscale perturbations and enforces cross-stream consistency to enhance pseudolabel reliability; and 3) decoupled optimization for multitask heads to resolve intertask gradient conflicts. Extensive experiments show DPCDO consistently outperforms state-of-the-art methods in both semantic segmentation and monocular height estimation, validating its effectiveness in disentangling domain shifts and enhancing cross-task synergy.
Zitong Wu, Yaoyao Yin, Biao Hou et al.· IEEE Transactions on Geoscie...· 0 citations
Remote sensing visual question answering (RSVQA) remains challenging because the evidence relevant to the question in remote sensing (RS) imagery is typically sparse, spatially dispersed, and highly variable in scale and layout. This structural heterogeneity poses a major challenge to existing transfer strategies, which often struggle to achieve effective query-conditioned semantic focusing and localized spatial refinement. To address this issue, we propose CRISP, a task-specific parameter-efficient adaptation framework for RSVQA built on a frozen ViLT backbone. CRISP comprises two complementary components. First, a cross-modal residual guidance (CMRG) module generates instance-specific guidance tokens from pooled image and question summaries, steering early cross-modal interaction toward query-relevant content while suppressing background interference. Second, an attention-guided spatial realignment (ASR) module performs offset-guided feature realignment within intermediate Transformer layers, enabling localized refinement of spatial evidence under scale variation and sparse semantic distribution. Extensive experiments on the RSVQA-LR and RSVQA-HR benchmarks show that CRISP achieves strong overall performance and consistently improves overall accuracy (OA) and average accuracy (AA) over prior methods, with particularly notable gains on presence, comparison, and region-related questions. These results demonstrate that residual guidance and spatial realignment together provide an effective task-specific parameter-efficient adaptation strategy for RSVQA under the frozen-backbone setting. The code will be available at https://github.com/PhD-Xu/CRISP
Chang Xu, Zhongle Ren, Biao Hou et al.· IEEE Transactions on Geoscie...· 0 citations