Online Continual Learning on Class Incremental Blurry Task Configuration with Anytime Inference

TL;DR

This paper introduces a practical online continual learning setup with blurry task boundaries and real-time inference, proposing a new metric and an effective method that significantly outperforms previous approaches.

Contribution

It presents a novel online, task-free, class-incremental setup with blurry boundaries and a new performance metric, along with an innovative method employing advanced memory management and learning techniques.

Findings

Proposed method outperforms prior arts by large margins.

New metric effectively measures performance in real-time inference scenarios.

Empirical validation confirms the practicality of the approach.

Abstract

Despite rapid advances in continual learning, a large body of research is devoted to improving performance in the existing setups. While a handful of work do propose new continual learning setups, they still lack practicality in certain aspects. For better practicality, we first propose a novel continual learning setup that is online, task-free, class-incremental, of blurry task boundaries and subject to inference queries at any moment. We additionally propose a new metric to better measure the performance of the continual learning methods subject to inference queries at any moment. To address the challenging setup and evaluation protocol, we propose an effective method that employs a new memory management scheme and novel learning techniques. Our empirical validation demonstrates that the proposed method outperforms prior arts by large margins. Code and data splits are available at https://github.com/naver-ai/i-Blurry.