The rapid growth of generative artificial intelligence has led to an explosion of multimodal data, intensifying the demand for adaptive cross-modal retrieval systems. However, persistent semantic and distributional gaps across modalities continue to hinder effective alignment. To alleviate these challenges without incurring prohibitive annotation costs, unsupervised cross-modal retrieval (UCMR) has emerged as an attractive alternative; nevertheless, it often struggles to establish reliable semantic correspondences due to the absence of supervision. To address this limitation, we propose multi-granularity consensus representation alignment (MiRA), an unsupervised framework that enhances semantic consistency and representation robustness via hierarchical, noise-aware learning. MiRA progressively refines multi-granular features and aligns cross-modal representations through consensus-driven optimization. Specifically, it comprises two key components: (1) progressive agreement clustering (PAC), which improves pseudo-label reliability by enforcing cross-layer consistency and reducing uncertainty from single-granularity representations; and (2) cross-modal robust association (CRA), which leverages the refined pseudo-labels to guide representation learning under a hybrid contrastive-consistency objective, promoting discriminative alignment while suppressing noisy associations. Extensive experiments on four benchmark datasets demonstrate that MiRA consistently surpasses nine state-of-the-art UCMR methods, confirming its effectiveness in capturing hierarchical semantics and achieving robust cross-modal alignment without supervision.
This paper addresses the degradation of imaging quality in high-resolution CubeSats caused by micro-vibrations from attitude control flywheels. It proposes a micro-vibration suppression scheme that incorporates multi-disciplinary integrated modeling, dual passive vibration isolation, and multi-level verification. A comprehensive model encompassing flywheel disturbance, optics, attitude control, and structure is developed to elucidate the transmission dynamics of micro-vibrations from the source to the optical payload. A dual suppression system utilizing silicone rubber isolators is engineered for both the disturbance source (flywheel) and the payload (optical camera). By optimizing stiffness matching and damping, it achieves a balance between isolation efficiency and stability in attitude control. A three-tier verification system comprising “numerical simulation–ground microgravity testing–on-orbit imaging” has been established. The findings indicate that the dual isolation system diminishes the pixel offset amplitude of the optical payload to under 0.1 pixels (down to the 0.02 pixel level in the high-frequency band), with an isolation efficiency of 80%. Consistent outcomes from terrestrial and orbital validation affirm the engineering viability of the plan. This research offers theoretical backing for the precise control of micro-vibrations in micro-nano satellites, thereby enhancing their utility in high-resolution remote sensing applications.
