用模块化设计让目标检测模型轻松新增类别，支持持续学习。
DitHub: A Modular Framework for Incremental Open-Vocabulary Object Detection
- 将增量适配模块比作代码分支，按需组合使用。
- 在ODinW-13和新基准上达当前最优性能。
- 适合需要持续扩展类别的实际检测系统开发。
开放词汇目标检测可通过简单文本提示泛化到任意类别。然而，如何适应罕见类别或增强在多个专业领域的表现仍至关重要。现有方法依赖单一权重的全局适配策略，我们提出模块化框架DitHub，构建并维护高效适配模块库。受版本控制系统启发，DitHub将专家模块视为可获取、可合并的分支。该方法首次系统研究了适配模块的组合特性。在ODinW-13和新提出的类目重现评估基准ODinW-O上均取得当前最优结果。
原文摘要 · Abstract (English)
Open-Vocabulary object detectors can generalize to an unrestricted set of categories through simple textual prompting. However, adapting these models to rare classes or reinforcing their abilities on multiple specialized domains remains essential. While recent methods rely on monolithic adaptation strategies with a single set of weights, we embrace modular deep learning. We introduce DitHub, a framework designed to build and maintain a library of efficient adaptation modules. Inspired by Version Control Systems, DitHub manages expert modules as branches that can be fetched and merged as needed. This modular approach allows us to conduct an in-depth exploration of the compositional properties of adaptation modules, marking the first such study in Object Detection. Our method achieves state-of-the-art performance on the ODinW-13 benchmark and ODinW-O, a newly introduced benchmark designed to assess class reappearance. For more details, visit our project page: https://aimagelab.github.io/DitHub/
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。