On Parameter Tuning in Meta-learning for Computer Vision
This work addresses parameter tuning for meta-learning in computer vision, but it appears incremental as it builds on existing methods like semantic auto-encoders.
The paper tackles the problem of parameter tuning in meta-learning for zero-shot learning in image recognition, achieving improved accuracy for a semantic auto-encoder by combining embedded parameters.
Learning to learn plays a pivotal role in meta-learning (MTL) to obtain an optimal learning model. In this paper, we investigate mage recognition for unseen categories of a given dataset with limited training information. We deploy a zero-shot learning (ZSL) algorithm to achieve this goal. We also explore the effect of parameter tuning on performance of semantic auto-encoder (SAE). We further address the parameter tuning problem for meta-learning, especially focusing on zero-shot learning. By combining different embedded parameters, we improved the accuracy of tuned-SAE. Advantages and disadvantages of parameter tuning and its application in image classification are also explored.