Searched for: subject%3A%22Label%255C%2Bselection%22
(1 - 1 of 1)
Burghouts, G.J. (author), Kruithof, M.C. (author), Huizinga, W. (author), Schutte, K. (author)
Learning object detection models with a few labels, is possible due to ingenious few-shot techniques, and due to clever selection of images to be labeled. Few-shot techniques work with as few as 1 to 10 randomized labels per object class. We are curious if performance of randomized label selection can be improved by selecting 1 to 10 labels per...
conference paper 2022