Search Results for author:
Found 2 papers, 0 papers with code
SML: Semantic Meta-learning for Few-shot Semantic Segmentation
In addition, we propose to use the well established technique, ridge regression, to not only bring in the class-level semantic information, but also to effectively utilise the information available from multiple images present in the training data for prototype computation.
Unified Generator-Classifier for Efficient Zero-Shot Learning
Generative models have achieved state-of-the-art performance for the zero-shot learning problem, but they require re-training the classifier every time a new object category is encountered.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
