From Semantics to Pixels: Coarse-to-Fine Masked Autoencoders for Hierarchical Visual Understanding

source_context

{
  "surface": "signal_canvas",
  "mode": "paper",
  "query": "From Semantics to Pixels: Coarse-to-Fine Masked Autoencoders for Hierarchical Visual Understanding",
  "normalized_query": "2603.09955",
  "route": "/signal-canvas/from-semantics-to-pixels-coarse-to-fine-masked-autoencoders-for-hierarchical-visual-understanding",
  "paper_ref": "from-semantics-to-pixels-coarse-to-fine-masked-autoencoders-for-hierarchical-visual-understanding",
  "topic_slug": null,
  "benchmark_ref": null,
  "dataset_ref": null
}