Densifying Supervision for Fine-Grained Visual Comparisons
International Journal of Computer Vision, pp. 2704-2730, 2020.
Detecting subtle differences in visual attributes requires inferring which of two images exhibits a property more, e.g., which face is smiling slightly more, or which shoe is slightly more sporty. While valuable for applications ranging from biometrics to online shopping, fine-grained attributes are challenging to learn. Unlike traditiona...More
Full Text (Upload PDF)
PPT (Upload PPT)