MEGA Hub

CounterFactual Retrieval for Evidence-Aware Individual Animal Identification

Authors

Do you know Ankit K. Upadhyay?You can claim authorship or link another user.Do you know Aleksandr Algasov?You can claim authorship or link another user.Do you know Ekaterina Nepovinnykh?You can claim authorship or link another user.Do you know Fedor Zolotarev?You can claim authorship or link another user.Do you know Tuomas Eerola?You can claim authorship or link another user.Do you know Heikki Kälviäinen?You can claim authorship or link another user.Do you know Charles V. Stewart?You can claim authorship or link another user.Do you know Lukas Picek?You can claim authorship or link another user.

Abstract

Automated identification of individual animals is moving from small curated studies toward shared benchmarks and reusable foundation models. This progress is useful, but current evaluation leaves the evidence behind a match unresolved, i.e., high retrieval accuracy does not show whether a model used animal features or identity-correlated shortcuts. We address this with Counterfactual Foreground Retrieval (CFR), an evidence-aware evaluation protocol. CFR evaluates the same query-gallery task under different views: full image, foreground-only, and shortcut-only. The full-image measures standard retrieval performance; the foreground-only measures foreground-supported retrieval; and shortcut-only view measure how much identity signal is recoverable from background, or silhouette. This turns a retrieval score into an evidence profile: how well the model performs on the original images, how much of that performance remains when only the animal is visible, and how much identity signal remains recoverable when the animal is removed. We release around 0.5M masks for 34 datasets and code for mask generation and CFR evaluation.

Community

00

Publication notes

Author note
14 pages, 5 figures; accepted at WACV 2027