Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processes
This addresses the need for flexible and efficient multi-task classification systems in machine learning, with incremental improvements in adaptation and transfer learning.
The paper tackles the problem of designing image classification systems that can automatically adapt to new tasks at test time after multi-task training, achieving state-of-the-art results on the Meta-Dataset benchmark and demonstrating robustness across low-shot and high-shot regimes.
The goal of this paper is to design image classification systems that, after an initial multi-task training phase, can automatically adapt to new tasks encountered at test time. We introduce a conditional neural process based approach to the multi-task classification setting for this purpose, and establish connections to the meta-learning and few-shot learning literature. The resulting approach, called CNAPs, comprises a classifier whose parameters are modulated by an adaptation network that takes the current task's dataset as input. We demonstrate that CNAPs achieves state-of-the-art results on the challenging Meta-Dataset benchmark indicating high-quality transfer-learning. We show that the approach is robust, avoiding both over-fitting in low-shot regimes and under-fitting in high-shot regimes. Timing experiments reveal that CNAPs is computationally efficient at test-time as it does not involve gradient based adaptation. Finally, we show that trained models are immediately deployable to continual learning and active learning where they can outperform existing approaches that do not leverage transfer learning.