C3Box: A CLIP-based Class-Incremental Learning Toolbox
Hao Sun, Da-Wei Zhou

TL;DR
C3Box is a modular Python toolbox that unifies various CLIP-based class-incremental learning methods, facilitating reproducible experiments and benchmarking in continual learning research.
Contribution
It introduces a comprehensive, standardized framework for CLIP-based CIL, integrating multiple methods into a user-friendly, reproducible platform.
Findings
Provides a unified, modular framework for CLIP-based CIL methods.
Enables reproducible experiments with low engineering overhead.
Supports benchmarking and fair comparison of CIL approaches.
Abstract
Traditional machine learning systems are typically designed for static data distributions, which suffer from catastrophic forgetting when learning from evolving data streams. Class-Incremental Learning (CIL) addresses this challenge by enabling learning systems to continuously learn new classes while preserving prior knowledge. With the rise of pre-trained models (PTMs) such as CLIP, leveraging their strong generalization and semantic alignment capabilities has become a promising direction in CIL. However, existing CLIP-based CIL methods are often scattered across disparate codebases, rely on inconsistent configurations, hindering fair comparisons, reproducibility, and practical adoption. Therefore, we propose C3Box (CLIP-based Class-inCremental learning toolBOX), a modular and comprehensive Python toolbox. C3Box integrates representative traditional CIL methods, ViT-based CIL methods,…
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.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsDomain Adaptation and Few-Shot Learning · Data Stream Mining Techniques · Imbalanced Data Classification Techniques
