Low-Shot Learning from Imaginary 3D Model
It addresses data scarcity in fine-grained recognition, but the approach is incremental as it builds on existing few-shot learning methods.
The paper tackles the problem of few-shot learning in visual recognition by using a 3D model derived from training images to hallucinate novel viewpoints and poses for scarce samples, resulting in significant accuracy improvements on the CUB-200-2011 dataset.
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.