SAMCL: 通过极高效存储使SAM持续学习动态领域
SAMCL: Empowering SAM to Continually Learn from Dynamic Domains with Extreme Storage Efficiency
AI总结：
SAMCL通过高效存储和模块选择机制，使SAM在动态领域中实现持续学习，减少存储需求并提升领域适应性。
摘要：
Segment Anything Model（SAM）在开放世界场景中面对多样化的领域时表现不佳。在这样的情况下，使用精心设计的学习模块进行简单的微调是不够的，而且在逐步学习时常常导致灾难性遗忘问题。为了解决这个问题，我们提出了一种新的持续学习（CL）方法用于SAM，称为SAMCL。与其依赖于固定的模块，我们的方法将增量知识分解成单独的模块，并训练一个选择器在推理时选择适当的模块。然而，这种直观的设计引入了两个关键挑战：确保模块的有效学习和选择，以及随着任务的积累管理存储。为了解决这些挑战，我们引入了两个组件：AugModule和Module Selector。AugModule通过在层之间共享参数来减少流行LoRA学习模块的存储，同时保持准确性。它还利用从点提示生成的热图进一步增强领域适应，且以最小的额外成本实现。Module Selector利用SAM的嵌入可以有效区分领域的观察，通过在低消耗嵌入上训练而不是原始图像，实现了高选择准确性。实验表明，SAMCL优于最先进的方法，仅产生0.19%的遗忘，并在未见过的领域上至少获得2.5%的提升。每个AugModule只需要0.233 MB，将存储减少至少24.3%超过其他微调方法。Module Selector的缓冲存储进一步减少高达256倍。
英文摘要：
Segment Anything Model (SAM) struggles in open-world scenarios with diverse domains. In such settings, naive fine-tuning with a well-designed learning module is inadequate and often causes catastrophic forgetting issue when learning incrementally. To address this issue, we propose a novel continual learning (CL) method for SAM, termed SAMCL. Rather than relying on a fixed learning module, our method decomposes incremental knowledge into separate modules and trains a selector to choose the appropriate one during inference. However, this intuitive design introduces two key challenges: ensuring effective module learning and selection, and managing storage as tasks accumulate. To tackle these, we introduce two components: AugModule and Module Selector. AugModule reduces the storage of the popular LoRA learning module by sharing parameters across layers while maintaining accuracy. It also employs heatmaps-generated from point prompts-to further enhance domain adaptation with minimal additional cost. Module Selector leverages the observation that SAM's embeddings can effectively distinguish domains, enabling high selection accuracy by training on low-consumed embeddings instead of raw images. Experiments show that SAMCL outperforms state-of-the-art methods, achieving only 0.19% forgetting and at least 2.5% gain on unseen domains. Each AugModule requires just 0.233 MB, reducing storage by at least 24.3% over other fine-tuning approaches. The buffer storage for Module Selector is further reduced by up to 256$\times$.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
