Transductive One-Shot Learning Meet Subspace Decomposition
This addresses the problem of adapting pretrained models to recognize unseen classes from just one labeled image, which is incremental as it builds on existing one-shot learning methods.
The paper tackles one-shot learning by introducing a transductive approach using subspace decomposition to propagate labels from a single labeled image to unlabeled query images based on shared latent primitives, demonstrating effective generalization to novel classes.
One-shot learning focuses on adapting pretrained models to recognize newly introduced and unseen classes based on a single labeled image. While variations of few-shot and zero-shot learning exist, one-shot learning remains a challenging yet crucial problem due to its ability to generalize knowledge to unseen classes from just one human-annotated image. In this paper, we introduce a transductive one-shot learning approach that employs subspace decomposition to utilize the information from labeled images in the support set and unlabeled images in the query set. These images are decomposed into a linear combination of latent variables representing primitives captured by smaller subspaces. By representing images in the query set as linear combinations of these latent primitives, we can propagate the label from a single image in the support set to query images that share similar combinations of primitives. Through a comprehensive quantitative analysis across various neural network feature extractors and datasets, we demonstrate that our approach can effectively generalize to novel classes from just one labeled image.