Learning Classifiers for Domain Adaptation, Zero and Few-Shot Recognition Based on Learning Latent Semantic Parts
This addresses the challenge of insufficient training examples for new objects and environments in computer vision, though it appears incremental as it builds on existing adaptation methods.
The paper tackles the problem of adapting visual models to new scenarios with limited data, such as domain adaptation, zero-shot, and few-shot learning, by proposing a novel attribute encoding method based on prototypical part-type probabilities, and reports outperforming state-of-the-art methods on benchmark datasets.
In computer vision applications, such as domain adaptation (DA), few shot learning (FSL) and zero-shot learning (ZSL), we encounter new objects and environments, for which insufficient examples exist to allow for training "models from scratch," and methods that adapt existing models, trained on the presented training environment, to the new scenario are required. We propose a novel visual attribute encoding method that encodes each image as a low-dimensional probability vector composed of prototypical part-type probabilities. The prototypes are learnt to be representative of all training data. At test-time we utilize this encoding as an input to a classifier. At test-time we freeze the encoder and only learn/adapt the classifier component to limited annotated labels in FSL; new semantic attributes in ZSL. We conduct extensive experiments on benchmark datasets. Our method outperforms state-of-art methods trained for the specific contexts (ZSL, FSL, DA).