Recognizing Families through Images with Pretrained Encoder
This work addresses kinship recognition in computer vision, but it is incremental as it applies existing methods to a competition without major innovations.
The authors tackled kinship verification and retrieval using facial images, achieving 9th place in verification and 5th in retrieval in the Recognizing Family in The Wild 2020 competition by employing FaceNet, Siamese VGG-Face, and their combination as feature extractors.
Kinship verification and kinship retrieval are emerging tasks in computer vision. Kinship verification aims at determining whether two facial images are from related people or not, while kinship retrieval is the task of retrieving possible related facial images to a person from a gallery of images. They introduce unique challenges because of the hidden relations and features that carry inherent characteristics between the facial images. We employ 3 methods, FaceNet, Siamese VGG-Face, and a combination of FaceNet and VGG-Face models as feature extractors, to achieve the 9th standing for kinship verification and the 5th standing for kinship retrieval in the Recognizing Family in The Wild 2020 competition. We then further experimented using StyleGAN2 as another encoder, with no improvement in the result.