Deep Learning for Single-View Instance Recognition
This addresses the problem of recognizing object instances from novel viewpoints for applications with sparse product datasets, representing an incremental advance in deep learning for low-data scenarios.
The paper tackles single-view instance recognition with limited training data, showing that feedforward neural networks outperform state-of-the-art methods when trained from just one image per object, and further improves performance by using an auxiliary multi-view dataset to enhance robustness to viewpoint changes.
Deep learning methods have typically been trained on large datasets in which many training examples are available. However, many real-world product datasets have only a small number of images available for each product. We explore the use of deep learning methods for recognizing object instances when we have only a single training example per class. We show that feedforward neural networks outperform state-of-the-art methods for recognizing objects from novel viewpoints even when trained from just a single image per object. To further improve our performance on this task, we propose to take advantage of a supplementary dataset in which we observe a separate set of objects from multiple viewpoints. We introduce a new approach for training deep learning methods for instance recognition with limited training data, in which we use an auxiliary multi-view dataset to train our network to be robust to viewpoint changes. We find that this approach leads to a more robust classifier for recognizing objects from novel viewpoints, outperforming previous state-of-the-art approaches including keypoint-matching, template-based techniques, and sparse coding.