Deep Learning for Single-View Instance Recognition

TL;DR

This paper demonstrates that deep learning can effectively recognize object instances from a single view, especially when trained with an auxiliary multi-view dataset, outperforming traditional methods.

Contribution

The paper introduces a novel training approach using an auxiliary multi-view dataset to enhance deep learning-based instance recognition from limited data.

Findings

Feedforward neural networks outperform state-of-the-art methods with single images.

Using a multi-view auxiliary dataset improves robustness to viewpoint changes.

The proposed method surpasses keypoint-matching, template-based, and sparse coding approaches.

Abstract

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.