Prompt-based continual learning adapts a frozen pre-trained vision transformer by tuning a small set of prompt tokens. Recently, one-prompt methods which share one single prompt across all tasks ma...
<p><strong>Tác giả:</strong> Duy Cuong Bui, Trung-Anh Dang, Vincent Nguyen, Duc V. Le, Ngoc‐Son Vu</p>
<p>Prompt-based continual learning adapts a frozen pre-trained vision transformer by tuning a small set of prompt tokens. Recently, one-prompt methods which share one single prompt across all tasks make this paradigm maximally parameter efficient. The open question is how a shared prompt can keep the knowledge of old classes while being updated for new ones. Existing methods protect old knowledge in parameter space, where they freeze task-specific prompts, expand new components, or sparsely gate...</p>
<p>📄 DOI: <a href="https://doi.org/https://doi.org/10.48550/arxiv.2611.12777" target="_blank" rel="noopener">https://doi.org/10.48550/arxiv.2611.12777</a></p>
<p>📖 <a href="https://doi.org/https://doi.org/10.48550/arxiv.2611.12777" target="_blank" rel="noopener">Xem bài báo đầy đủ</a></p>
Bài viết được biên soạn lại bởi LIFVietnam. Nguồn tham khảo: OpenAlex
