Facial Image Feature Analysis and its Specialization for Fréchet Distance and Neighborhoods
This addresses the challenge of image distance assessment for vision researchers, but it is incremental as it builds on existing Fréchet distance methods by applying them to a specific domain.
The paper tackled the problem of assessing distances between images and datasets by analyzing domain-specific feature training for Fréchet distance, focusing on facial images, and found that specialization improves distance metrics based on experiments and user studies.
Assessing distances between images and image datasets is a fundamental task in vision-based research. It is a challenging open problem in the literature and despite the criticism it receives, the most ubiquitous method remains the Fréchet Inception Distance. The Inception network is trained on a specific labeled dataset, ImageNet, which has caused the core of its criticism in the most recent research. Improvements were shown by moving to self-supervision learning over ImageNet, leaving the training data domain as an open question. We make that last leap and provide the first analysis on domain-specific feature training and its effects on feature distance, on the widely-researched facial image domain. We provide our findings and insights on this domain specialization for Fréchet distance and image neighborhoods, supported by extensive experiments and in-depth user studies.