TL;DR
PrePrompt introduces a novel class incremental learning framework that predicts task-specific prompts using pre-trained models, effectively balancing stability and plasticity to outperform existing prompt-based methods.
Contribution
The paper proposes PrePrompt, a new CIL framework that predicts prompts directly from pre-trained models, overcoming correlation-based limitations and improving performance.
Findings
PrePrompt outperforms state-of-the-art prompt-based CIL methods on multiple benchmarks.
Feature translation helps balance stability and plasticity in incremental learning.
The approach effectively mitigates bias towards recent classes.
Abstract
Class Incremental Learning (CIL) based on pre-trained models offers a promising direction for open-world continual learning. Existing methods typically rely on correlation-based strategies, where an image's classification feature is used as a query to retrieve the most related key prompts and select the corresponding value prompts for training. However, these approaches face an inherent limitation: fitting the entire feature space of all tasks with only a few trainable prompts is fundamentally challenging. We propose Predictive Prompting (PrePrompt), a novel CIL framework that circumvents correlation-based limitations by leveraging pre-trained models' natural classification ability to predict task-specific prompts. Specifically, PrePrompt decomposes CIL into a two-stage prediction framework: task-specific prompt prediction followed by label prediction. While theoretically appealing,…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
