Аннотация
Distance metric learning (DML) has been successfully applied to object
classification, both in the standard regime of rich training data and in the
few-shot scenario, where each category is represented by only few examples. In
this work, we propose a new method for DML, featuring a joint learning of the
embedding space and of the data distribution of the training categories, in a
single training process. Our method improves upon leading algorithms for
DML-based object classification. Furthermore, it opens the door for a new task
in Computer Vision - a few-shot object detection, since the proposed DML
architecture can be naturally embedded as the classification head of any
standard object detector. In numerous experiments, we achieve state-of-the-art
classification results on a variety of fine-grained datasets, and offer the
community a benchmark on the few-shot detection task, performed on the
Imagenet-LOC dataset. The code will be made available upon acceptance.
Пользователи данного ресурса
Пожалуйста,
войдите в систему, чтобы принять участие в дискуссии (добавить собственные рецензию, или комментарий)