SOURCE-LINKED INTELLIGENCE

The Visual Target Matters: Learning across the Visual Hierarchy for Brain-to-Image Retrieval

arXiv · AI, language, vision and robotics · article · Sep 21, 2026 · UTC

Brain-to-image retrieval seeks to identify the visual stimulus that elicited a non-invasive neural response. Candidate images are typically represented by pretrained vision models, whose internal representations vary in abstraction across depth. Existing methods usually train the neural encoder to recover a fixed final-layer visual target. Under this formulation, the visual hierarchy is reduced to a single prescribed endpoint, preventing representations at other depths from directly shaping the visual target. This limitation motivates learning how information across visual depths should contri

Read original source ↗ Open in workspace

recordType

paper

region

Global