PL-FSCIL: Harnessing the Power of Prompts for Few-Shot Class-Incremental Learning

TL;DR

This paper introduces PL-FSCIL, a prompt-based method using a pre-trained Vision Transformer to improve few-shot class-incremental learning, demonstrating competitive results on benchmark datasets.

Contribution

It pioneers the use of visual prompts in FSCIL, combining domain and task-specific prompts within a ViT model to enhance incremental learning with limited data.

Findings

Achieves competitive performance on CIFAR-100 and CUB-200 datasets.

Demonstrates the effectiveness of visual prompts in FSCIL tasks.

Shows potential for real-world applications with scarce data.

Abstract

Few-Shot Class-Incremental Learning (FSCIL) aims to enable deep neural networks to learn new tasks incrementally from a small number of labeled samples without forgetting previously learned tasks, closely mimicking human learning patterns. In this paper, we propose a novel approach called Prompt Learning for FSCIL (PL-FSCIL), which harnesses the power of prompts in conjunction with a pre-trained Vision Transformer (ViT) model to address the challenges of FSCIL effectively. Our work pioneers the use of visual prompts in FSCIL, which is characterized by its notable simplicity. PL-FSCIL consists of two distinct prompts: the Domain Prompt and the FSCIL Prompt. Both are vectors that augment the model by embedding themselves into the attention layer of the ViT model. Specifically, the Domain Prompt assists the ViT model in adapting to new data domains. The task-specific FSCIL Prompt, coupled with a prototype classifier, amplifies the model's ability to effectively handle FSCIL tasks. We validate the efficacy of PL-FSCIL on widely used benchmark datasets such as CIFAR-100 and CUB-200. The results showcase competitive performance, underscoring its promising potential for real-world applications where high-quality data is often scarce. The source code is available at: https://github.com/TianSongS/PL-FSCIL.