Joint Input and Output Coordination for Class-Incremental Learning

TL;DR

This paper introduces a joint input and output coordination mechanism for class-incremental learning that effectively reduces catastrophic forgetting, addresses class bias, and minimizes interference between old and new tasks, improving overall performance.

Contribution

The paper proposes a novel joint input and output coordination mechanism that enhances class-incremental learning by addressing class bias and task interference, and can be integrated into existing methods.

Findings

Significant performance improvements across multiple benchmarks.

Effective reduction of class bias and mutual interference.

Versatile mechanism compatible with various incremental learning approaches.

Abstract

Incremental learning is nontrivial due to severe catastrophic forgetting. Although storing a small amount of data on old tasks during incremental learning is a feasible solution, current strategies still do not 1) adequately address the class bias problem, and 2) alleviate the mutual interference between new and old tasks, and 3) consider the problem of class bias within tasks. This motivates us to propose a joint input and output coordination (JIOC) mechanism to address these issues. This mechanism assigns different weights to different categories of data according to the gradient of the output score, and uses knowledge distillation (KD) to reduce the mutual interference between the outputs of old and new tasks. The proposed mechanism is general and flexible, and can be incorporated into different incremental learning approaches that use memory storage. Extensive experiments show that our mechanism can significantly improve their performance.