DSS-Prompt: Dynamic-Static Synergistic Prompting for Few-Shot Class-Incremental Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: He, Linpu, Li, Yanan, Li, Bingze, Cui, Elvis Han, Wang, Donghui
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915444287340544
author He, Linpu
Li, Yanan
Li, Bingze
Cui, Elvis Han
Wang, Donghui
author_facet He, Linpu
Li, Yanan
Li, Bingze
Cui, Elvis Han
Wang, Donghui
contents Learning from large-scale pre-trained models with strong generalization ability has shown remarkable success in a wide range of downstream tasks recently, but it is still underexplored in the challenging few-shot class-incremental learning (FSCIL) task. It aims to continually learn new concepts from limited training samples without forgetting the old ones at the same time. In this paper, we introduce DSS-Prompt, a simple yet effective approach that transforms the pre-trained Vision Transformer with minimal modifications in the way of prompts into a strong FSCIL classifier. Concretely, we synergistically utilize two complementary types of prompts in each Transformer block: static prompts to bridge the domain gap between the pre-training and downstream datasets, thus enabling better adaption; and dynamic prompts to capture instance-aware semantics, thus enabling easy transfer from base to novel classes. Specially, to generate dynamic prompts, we leverage a pre-trained multi-modal model to extract input-related diverse semantics, thereby generating complementary input-aware prompts, and then adaptively adjust their importance across different layers. In this way, on top of the prompted visual embeddings, a simple prototype classifier can beat state-of-the-arts without further training on the incremental tasks. We conduct extensive experiments on four benchmarks to validate the effectiveness of our DSS-Prompt and show that it consistently achieves better performance than existing approaches on all datasets and can alleviate the catastrophic forgetting issue as well.
format Preprint
id arxiv_https___arxiv_org_abs_2508_09785
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DSS-Prompt: Dynamic-Static Synergistic Prompting for Few-Shot Class-Incremental Learning
He, Linpu
Li, Yanan
Li, Bingze
Cui, Elvis Han
Wang, Donghui
Computer Vision and Pattern Recognition
Learning from large-scale pre-trained models with strong generalization ability has shown remarkable success in a wide range of downstream tasks recently, but it is still underexplored in the challenging few-shot class-incremental learning (FSCIL) task. It aims to continually learn new concepts from limited training samples without forgetting the old ones at the same time. In this paper, we introduce DSS-Prompt, a simple yet effective approach that transforms the pre-trained Vision Transformer with minimal modifications in the way of prompts into a strong FSCIL classifier. Concretely, we synergistically utilize two complementary types of prompts in each Transformer block: static prompts to bridge the domain gap between the pre-training and downstream datasets, thus enabling better adaption; and dynamic prompts to capture instance-aware semantics, thus enabling easy transfer from base to novel classes. Specially, to generate dynamic prompts, we leverage a pre-trained multi-modal model to extract input-related diverse semantics, thereby generating complementary input-aware prompts, and then adaptively adjust their importance across different layers. In this way, on top of the prompted visual embeddings, a simple prototype classifier can beat state-of-the-arts without further training on the incremental tasks. We conduct extensive experiments on four benchmarks to validate the effectiveness of our DSS-Prompt and show that it consistently achieves better performance than existing approaches on all datasets and can alleviate the catastrophic forgetting issue as well.
title DSS-Prompt: Dynamic-Static Synergistic Prompting for Few-Shot Class-Incremental Learning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.09785