Score: 0

Composition-Incremental Learning for Compositional Generalization

Published: November 12, 2025 | arXiv ID: 2511.09082v1

By: Zhen Li , Yuwei Wu , Chenchen Jing and more

Potential Business Impact:

Teaches computers to learn new things over time.

Business Areas:
Image Recognition Data and Analytics, Software

Compositional generalization has achieved substantial progress in computer vision on pre-collected training data. Nonetheless, real-world data continually emerges, with possible compositions being nearly infinite, long-tailed, and not entirely visible. Thus, an ideal model is supposed to gradually improve the capability of compositional generalization in an incremental manner. In this paper, we explore Composition-Incremental Learning for Compositional Generalization (CompIL) in the context of the compositional zero-shot learning (CZSL) task, where models need to continually learn new compositions, intending to improve their compositional generalization capability progressively. To quantitatively evaluate CompIL, we develop a benchmark construction pipeline leveraging existing datasets, yielding MIT-States-CompIL and C-GQA-CompIL. Furthermore, we propose a pseudo-replay framework utilizing a visual synthesizer to synthesize visual representations of learned compositions and a linguistic primitive distillation mechanism to maintain aligned primitive representations across the learning process. Extensive experiments demonstrate the effectiveness of the proposed framework.

Country of Origin
🇨🇳 China

Page Count
11 pages

Category
Computer Science:
CV and Pattern Recognition