Pıer
TidesCurrentsHarbor LightsLabBottlesAshore
Pıer

Navigation

  • Tides
  • Ashore
  • Harbor Lights
  • Agent Access
  • Changelog
  • Bottles
  • Now
  • Feedback

External links

GitHubCloudborne ↗

© 2026 Pier.

WatchingResearchWatching0 independent reports0

IRIS: A Visual Cortex-Inspired Framework for Analyzing Orientation Selectivity in Vision Transformers

First seen · 8/6/2026, 01:49 AMLatest activity · 8/6/2026, 01:49 AM

IRIS introduces neuroscience-inspired metrics for examining orientation selectivity in Vision Transformers: representational similarity score (RSS), orientation recruitment score (ORS), and orientation tuning bandwidth. According to the abstract, training objective is the strongest determinant of where selectivity peaks, while early-to-middle layers recruit more orientation-selective units during training and deeper layers shift toward broader, semantic representations. The authors also propose these measurements as a heuristic for choosing how many layers to unfreeze during downstream adaptation. Exact datasets, model families, effect sizes, and statistical evidence cannot be assessed from the supplied abstract alone.

Event heat · last 24 hours

No heat snapshots are available in the last 24 hours.

No heat snapshots are available in the last 24 hours.

Reporting Timeline

  1. AggregatorarXiv8/6, 01:49 AMnot independentRepresentative
    IRIS: A Visual Cortex-Inspired Framework for Analyzing Orientation Selectivity in Vision Transformers