解决CLIP模型增量学习中的知识干扰问题，提升任务识别准确性。
GR4CIL: Gap-compensated Routing for CLIP-based Class Incremental Learning
- 通过分离视觉与文本知识，实现任务间知识隔离。
- 引入正交补偿机制，扩大正确任务得分差距。
- 适合需要持续学习新类别且保持泛化能力的场景。
类别增量学习（CIL）旨在持续学习新类别同时保留旧知识。尽管基于对比语言-图像预训练（CLIP）的模型展现出强大泛化能力，但现有方法仍面临两大挑战：共享参数适配易引发旧知识漂移，而任务特定知识组织常导致跨任务响应校准不良，影响可靠路由。为此，我们提出GR4CIL框架，结合任务区分与知识路由机制。该框架在保持增量稳定共享文本语义空间的同时，保留任务特定视觉知识，从而减少任务间干扰。此外，我们引入正交补偿机制，缓解模态差距引起的偏倚，增强任务内区分度，并扩大真实任务与竞争任务之间的得分差距。结果表明，GR4CIL能实现更可靠的任务感知知识路由，同时保持零样本泛化能力。在多个基准测试中，其性能持续优于强基线方法。
原文摘要 · Abstract (English)
Class-Incremental Learning (CIL) aims to continuously acquire new categories while preserving previously learned knowledge. Recently, Contrastive Language-Image Pre-trained (CLIP) models have shown strong potential for CIL due to their powerful generalization ability. However, existing methods still face two key challenges: shared-parameter adaptation tends to cause old-knowledge drift, and task-specific knowledge organization often leads to poorly calibrated cross-task responses, making reliable routing difficult. To address these issues, we propose GR4CIL, a framework combining task discrimination and knowledge routing for CLIP-based CIL. GR4CIL preserves task-specific visual knowledge while maintaining an incrementally stable shared textual semantic space, thereby reducing interference across tasks. Moreover, we introduce an orthogonal compensation mechanism to mitigate modality-gap-induced bias, enhance within-task discrimination, and enlarge the score margin between the ground-truth task and competing tasks. As a result, GR4CIL enables more reliable task-aware routing over learned knowledge while retaining the zero-shot generalization capability. Experiments on multiple benchmarks show that GR4CIL consistently outperforms strong baselines.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。