MindStrata: Learning Robust Multi-Subject Cortical Visual Representations via Stratified Layout-Semantics Decoding

Decoding cortical visual representations that generalize across human subjects remains challenging due to (i) limited modeling of compositional semantics and structured layout in multi-object scenes, (ii) brain functional differences across subjects, and (iii) evaluation protocols dominated by feature-based scores that are often misaligned with human perception. To address these challenges, we propose __MindStrata__, a neuro-cognitively inspired framework for multi-subject brain-to-scene decoding via stratified modeling. __MindStrata__ maps fMRI into structured brain-scene representations using two complementary branches: a ventral-like branch decodes multi-level semantics (object$\to$instances$\to$scene) in a CLIP-aligned space, while a dorsal-like branch decodes multi-scale spatial organization (target$\to$surrounding$\to$global) within latent layout space. A Brain-Scene Routing Controller integrates these stratified semantic and spatial cues for structure-guided reconstruction. To mitigate multi-subject variability, we further introduce Consistency-based Functional Alignment, combining subject-specific normalization with a relational consistency loss. We also propose the __Semantic Faithfulness Evaluation Protocol__ that evaluates description-, category-, count-, and position-level correctness and aligns more closely with human preferences Experiments demonstrate fine-grained layout and semantic decoding across single-subject, multi-subject, and data-limited settings, reveal ROI-specific spatial localization, and show robust reconstruction performance under progressively reduced fMRI spatial resolution. Code will be publicly released.