让分割模型持续学习新数据，避免遗忘旧知识。
OVS Meets Continual Learning: Towards Sustainable Open-Vocabulary Segmentation
- 用专家混合框架动态选择适合的分割模块
- 在连续增量数据下性能优于现有方法
- 适合需要长期更新的开放词汇分割场景
开放词汇分割（OVS）旨在识别训练数据中未出现的类别。然而，现有研究通常假设训练数据固定不变，忽略了实际中数据持续收集的场景。本文分析了现有OVS模型在此条件下的表现，探索了重训练、微调和持续学习等方法，发现均有明显局限。为此，提出基于专家混合框架的ConOVS方法，根据输入样本属于各增量数据分布的概率，动态组合专家解码器。大量实验表明，ConOVS在预训练、增量学习和零样本测试数据集上均持续优于现有方法，有效提升了数据序列化收集时OVS模型的识别能力。
原文摘要 · Abstract (English)
Open-Vocabulary Segmentation (OVS) aims to segment classes that are not present in the training dataset. However, most existing studies assume that the training data is fixed in advance, overlooking more practical scenarios where new datasets are continuously collected over time. To address this, we first analyze how existing OVS models perform under such conditions. In this context, we explore several approaches such as retraining, fine-tuning, and continual learning but find that each of them has clear limitations. To address these issues, we propose ConOVS, a novel continual learning method based on a Mixture-of-Experts framework. ConOVS dynamically combines expert decoders based on the probability that an input sample belongs to the distribution of each incremental dataset. Through extensive experiments, we show that ConOVS consistently outperforms existing methods across pre-training, incremental, and zero-shot test datasets, effectively expanding the recognition capabilities of OVS models when data is collected sequentially.
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。