Abstract | ||
---|---|---|
Human vision is able to immediately recognize novel visual categories after seeing just one or a few training examples. We describe how to add a similar capability to ConvNet classifiers by directly setting the final layer weights from novel training examples during low-shot learning. We call this process weight imprinting as it directly sets weights for a new category based on an appropriately scaled copy of the embedding layer activations for that training example. The imprinting process provides a valuable complement to training with stochastic gradient descent, as it provides immediate good classification performance and an initialization for any further fine-tuning in the future. We show how this imprinting process is related to proxy-based embeddings. However, it differs in that only a single imprinted weight vector is learned for each novel category, rather than relying on a nearest-neighbor distance to training instances as typically used with embedding methods. Our experiments show that using averaging of imprinted weights provides better generalization than using nearest-neighbor instance embeddings. |
Year | Venue | Field |
---|---|---|
2017 | arXiv: Computer Vision and Pattern Recognition | Stochastic gradient descent,Embedding,Pattern recognition,Computer science,Weight,Artificial intelligence,Initialization |
DocType | Volume | Citations |
Journal | abs/1712.07136 | 0 |
PageRank | References | Authors |
0.34 | 0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
hang qi | 1 | 0 | 1.69 |
M. Brown | 2 | 2474 | 175.45 |
D. G. Lowe | 3 | 15718 | 1413.60 |