用相似网络实现跨域实例标注，无需微调即可精准预测物体边界。
Interactive Instance Annotation with Siamese Networks
- 基于孪生网络设计，输入边界框即可预测物体轮廓。
- 跨数据集测试达当前最优，无需微调适应新场景。
- 适合需要快速标注未知对象的跨域视觉任务研究者。
标注实例掩码耗时费力。现有方法多依赖深度学习模型预测轮廓，再由人工修正，但主要针对同域场景，难以应对跨域标注任务。本文提出 SiamAnno 框架，受目标追踪中孪生网络启发，利用一次学习能力，仅以边界框为输入，预测未见过物体的边界，供标注者调整。在未进行微调的情况下，于多个数据集上训练与测试，均达到当前最优性能，证明其对领域和环境变化的强鲁棒性。相比以往工作，本研究提供更全面的实验结果，为后续研究建立坚实基准。据我们所知，SiamAnno 是首个探索孪生架构用于实例标注的模型。
原文摘要 · Abstract (English)
Annotating instance masks is time-consuming and labor-intensive. A promising solution is to predict contours using a deep learning model and then allow users to refine them. However, most existing methods focus on in-domain scenarios, limiting their effectiveness for cross-domain annotation tasks. In this paper, we propose SiamAnno, a framework inspired by the use of Siamese networks in object tracking. SiamAnno leverages one-shot learning to annotate previously unseen objects by taking a bounding box as input and predicting object boundaries, which can then be adjusted by annotators. Trained on one dataset and tested on another without fine-tuning, SiamAnno achieves state-of-the-art (SOTA) performance across multiple datasets, demonstrating its ability to handle domain and environment shifts in cross-domain tasks. We also provide more comprehensive results compared to previous work, establishing a strong baseline for future research. To our knowledge, SiamAnno is the first model to explore Siamese architecture for instance annotation.
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。