Are you In or Out (of gallery)? Wisdom from the Same-Identity Crowd
Aman Bhatta, Maria Dhakal, Michael C. King, Kevin W. Bowyer

TL;DR
This paper proposes a novel classifier-based method to determine if a probe face is in or out of the gallery, improving accuracy across various conditions and demographics by leveraging additional enrolled images.
Contribution
It introduces a new approach that uses enrolled images to predict Out-of-gallery status, outperforming threshold-based methods and applicable to degraded probe images.
Findings
Effective across diverse image conditions
Consistent accuracy across demographic groups
Better performance with advanced margin-based face matchers
Abstract
A central problem in one-to-many facial identification is that the person in the probe image may or may not have enrolled image(s) in the gallery; that is, may be In-gallery or Out-of-gallery. Past approaches to detect when a rank-one result is Out-of-gallery have mostly focused on finding a suitable threshold on the similarity score. We take a new approach, using the additional enrolled images of the identity with the rank-one result to predict if the rank-one result is In-gallery / Out-of-gallery. Given a gallery of identities and images, we generate In-gallery and Out-of-gallery training data by extracting the ranks of additional enrolled images corresponding to the rank-one identity. We then train a classifier to utilize this feature vector to predict whether a rank-one result is In-gallery or Out-of-gallery. Using two different datasets and four different matchers, we present…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsPublic Spaces through Art
