# Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processes

## TL;DR

This paper introduces CNAPs, a conditional neural process-based method for multi-task image classification that adapts quickly to new tasks without gradient updates, achieving state-of-the-art results efficiently.

## Contribution

The paper presents a novel CNAPs approach that enables fast, flexible, and robust multi-task classification with immediate deployment capabilities, advancing transfer learning techniques.

## Key findings

- Achieves state-of-the-art results on Meta-Dataset benchmark.
- Robust to low-shot and high-shot regimes.
- Computationally efficient at test-time without gradient updates.

## Abstract

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.