Low-Shot Learning from Imaginary 3D Model
Abstract
Since the advent of deep learning, neural networks have demonstrated remarkable results in many visual recognition tasks, constantly pushing the limits. However, the state-of-the-art approaches are largely unsuitable in scarce data regimes. To address this shortcoming, this paper proposes employing a 3D model, which is derived from training images. Such a model can then be used to hallucinate novel viewpoints and poses for the scarce samples of the few-shot learning scenario. A self-paced learning approach allows for the selection of a diverse set of high-quality images, which facilitates the training of a classifier. The performance of the proposed approach is showcased on the fine-grained CUB-200-2011 dataset in a few-shot setting and significantly improves our baseline accuracy.
Cite
@article{arxiv.1901.01868,
title = {Low-Shot Learning from Imaginary 3D Model},
author = {Frederik Pahde and Mihai Puscas and Jannik Wolff and Tassilo Klein and Nicu Sebe and Moin Nabi},
journal= {arXiv preprint arXiv:1901.01868},
year = {2019}
}
Comments
To appear at WACV 2019. arXiv admin note: text overlap with arXiv:1811.09192