CounterFactual Retrieval for Evidence-Aware Individual Animal Identification

The paper introduces Counterfactual Foreground Retrieval (CFR), an evidence‑aware evaluation protocol for automated individual animal identification. CFR assesses retrieval performance under three conditions: full images, foreground‑only, and shortcut‑only (background or silhouette). By comparing these views, CFR produces an evidence profile that reveals whether models rely on animal features or on identity‑correlated shortcuts, and the authors provide masks and code for 34 datasets to support this analysis.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• benchmarks