Skip to main content
Search

# Representation Analysis

1 related articles

Subscribe to updates
  1. arXiv

    How far a shared linear map suffices to predict feature changes from image edits: probe comparisons across ConvNeXt, SwinV2, and DINOv3

    The work trains probes of increasing capacity, from a spatially shared linear map to nonlinear per-vector, receptive-field, and global transformer models, to predict feature-space changes induced by geometric transforms, photometric edits, occlusions, and diffusion-generated semantic edits, finding that across ConvNeXt, SwinV2, and DINOv3 a single shared linear map often predicts held-out manipulation outcomes nearly as well as substantially more expressive probes for the supervised backbones, with sufficiency generally increasing with depth, while this pattern is less consistent for DINOv3.

You’re all caught up