A Unified Approach to Kinship Verification
In this work, we propose a deep learning-based approach for kin verification using a unified multi-task learning scheme where all kinship classes are jointly learned. This allows us to better utilize small training sets that are typical of kin verification. We introduce a novel approach for fusing t...
Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 43(2021), 8 vom: 01. Aug., Seite 2851-2857 |
---|---|
1. Verfasser: | |
Weitere Verfasser: | |
Format: | Online-Aufsatz |
Sprache: | English |
Veröffentlicht: |
2021
|
Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence |
Schlagworte: | Journal Article |
Zusammenfassung: | In this work, we propose a deep learning-based approach for kin verification using a unified multi-task learning scheme where all kinship classes are jointly learned. This allows us to better utilize small training sets that are typical of kin verification. We introduce a novel approach for fusing the embeddings of kin images, to avoid overfitting, which is a common issue in training such networks. An adaptive sampling scheme is derived for the training set images, to resolve the inherent imbalance in kin verification datasets. A thorough ablation study exemplifies the effectivity of our approach, which is experimentally shown to outperform contemporary state-of-the-art kin verification results when applied to the Families In the Wild, FG2018, and FG2020 datasets |
---|---|
Beschreibung: | Date Completed 13.09.2023 Date Revised 13.09.2023 published: Print-Electronic Citation Status MEDLINE |
ISSN: | 1939-3539 |
DOI: | 10.1109/TPAMI.2020.3036993 |