Category Ranking
98%
Total Visits
921
Avg Visit Duration
2 minutes
Citations
20
Article Abstract
Few-shot class-incremental learning (FSCIL) aims to learn new classes incrementally with a limited number of samples per class. Foundation models combined with prompt tuning showcase robust generalization and zero-shot learning (ZSL) capabilities, endowing them with potential advantages in transfer capabilities for FSCIL. However, existing prompt tuning methods excel in optimizing for stationary datasets, diverging from the inherent sequential nature in the FSCIL paradigm. To address this issue, taking inspiration from the "fast and slow mechanism" of the complementary learning systems (CLSs) in the brain, we present fast- and slow-update prompt tuning FSCIL (FSPT-FSCIL), a brain-inspired prompt tuning method for transferring foundation models to the FSCIL task. We categorize the prompts into two groups: fast-update prompts and slow-update prompts, which are interactively trained through meta-learning. Fast-update prompts aim to learn new knowledge within a limited number of iterations, while slow-update prompts serve as meta-knowledge and aim to strike a balance between rapid learning and avoiding catastrophic forgetting. Through experiments on multiple benchmark tests, we demonstrate the effectiveness and superiority of FSPT-FSCIL. The code is available at https://github.com/qihangran/FSPT-FSCIL.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1109/TNNLS.2024.3454237 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Temporal Modeling With Frozen Vision-Language Foundation Models for Parameter-Efficient Text-Video Retrieval.
IEEE Trans Neural Netw Learn Syst
September 2025
Temporal modeling plays an important role in the effective adaption of the powerful pretrained text-image foundation model into text-video retrieval. However, existing methods often rely on additional heavy trainable modules, such as transformer or BiLSTM, which are inefficient. In contrast, we avoid introducing such heavy components by leveraging frozen foundation models.
View Article and Find Full Text PDFEarly Detection of Lung Metastases in Breast Cancer Using YOLOv10 and Transfer Learning: A Diagnostic Accuracy Study.
Med Sci Monit
September 2025
Department of Radiology, Faculty of Medicine, Erzincan Binali Yildirim University, Erzincan, Turkey.
BACKGROUND This study used CT imaging analyzed with deep learning techniques to assess the diagnostic accuracy of lung metastasis detection in patients with breast cancer. The aim of the research was to create and verify a system for detecting malignant and metastatic lung lesions that uses YOLOv10 and transfer learning. MATERIAL AND METHODS From January 2023 to 2024, CT scans of 16 patients with breast cancer who had confirmed lung metastases were gathered retrospectively from Erzincan Mengücek Gazi Training and Research Hospital.
View Article and Find Full Text PDFDevelopment and evaluation of a lightweight large language model chatbot for medication enquiry.
PLOS Digit Health
September 2025
Singapore Health Services, Artificial Intelligence Office, Singapore.
Large Language Models (LLMs) show promise in augmenting digital health applications. However, development and scaling of large models face computational constraints, data security concerns and limitations of internet accessibility in some regions. We developed and tested Med-Pal, a medical domain-specific LLM-chatbot fine-tuned with a fine-grained, expert curated medication-enquiry dataset consisting of 1,100 question and answer pairs.
View Article and Find Full Text PDFPay more attention to the robustness of LLMs on adversarial prompt for instruction data mining.
Neural Netw
August 2025
National Key Laboratory of Parallel and Distributed Computing, College of Computer Science and Technology, National University of Defense Technology, Hunan Changsha, 410073, China. Electronic address:
Instruction tuning has emerged as a paramount method for tailoring the behaviors of LLMs. Recent studies have unveiled the potential for LLMs to achieve high performance through fine-tuning with a limited quantity of high-quality instruction data. Instruction-Following Difficulty is one of the most representative approaches in instruction data mining, which involves selecting samples where LLMs fail to generate response that align with the provided instructions as the high-quality instruction data.
View Article and Find Full Text PDFMedical Entity Linking in Low-Resource Settings with Fine-Tuning-Free LLMs.
Stud Health Technol Inform
September 2025
Chair of Medical Informatics, Institute of AI and Informatics in Medicine (AIIM), TUM University Hospital, Technical University of Munich, Munich, Germany.
Introduction: Medical entity linking is an important task in biomedical natural language processing, aiming to align textual mentions of medical concepts with standardized concepts in ontologies. Most existing approaches rely on supervised models or domain-specific embeddings, which require large datasets and significant computational resources.
Objective: The objective of this work is (1) to investigate the effectiveness of large language models (LLMs) in improving both candidate generation and disambiguation for medical entity linking through synonym expansion and in-context learning, and (2) to evaluate this approach against traditional string-matching and supervised methods.