PKI: Prior Knowledge-Infused Neural Network for Few-Shot Class-Incremental Learning

TL;DR

This paper introduces PKI, a neural network architecture that effectively leverages prior knowledge through an ensemble of projectors to improve few-shot class-incremental learning, addressing catastrophic forgetting and overfitting.

Contribution

The paper proposes a novel PKI framework with cascading projectors and variants to balance resource use and performance in FSCIL, outperforming existing methods.

Findings

PKI achieves superior accuracy on three benchmarks.

Cascading projectors effectively integrate prior knowledge.

Variants reduce resource consumption with minimal performance loss.

Abstract

Few-shot class-incremental learning (FSCIL) aims to continually adapt a model on a limited number of new-class examples, facing two well-known challenges: catastrophic forgetting and overfitting to new classes. Existing methods tend to freeze more parts of network components and finetune others with an extra memory during incremental sessions. These methods emphasize preserving prior knowledge to ensure proficiency in recognizing old classes, thereby mitigating catastrophic forgetting. Meanwhile, constraining fewer parameters can help in overcoming overfitting with the assistance of prior knowledge. Following previous methods, we retain more prior knowledge and propose a prior knowledge-infused neural network (PKI) to facilitate FSCIL. PKI consists of a backbone, an ensemble of projectors, a classifier, and an extra memory. In each incremental session, we build a new projector and add it to the ensemble. Subsequently, we finetune the new projector and the classifier jointly with other frozen network components, ensuring the rich prior knowledge is utilized effectively. By cascading projectors, PKI integrates prior knowledge accumulated from previous sessions and learns new knowledge flexibly, which helps to recognize old classes and efficiently learn new classes. Further, to reduce the resource consumption associated with keeping many projectors, we design two variants of the prior knowledge-infused neural network (PKIV-1 and PKIV-2) to trade off a balance between resource consumption and performance by reducing the number of projectors. Extensive experiments on three popular benchmarks demonstrate that our approach outperforms state-of-the-art methods.