轻量级适配器让SAM3高效用于图像分割任务
SAM3-UNet: Simplified Adaptation of Segment Anything Model 3
- 用简单适配器+轻量解码器，低成本微调SAM3
- 在多个任务上超越SAM2-UNet，训练仅需<6GB显存
- 适合资源有限但需高精度分割的工程应用
本文提出SAM3-UNet，一种简化版的Segment Anything Model 3（SAM3）变体，旨在以低开销适配下游任务。该模型由三部分构成：SAM3图像编码器、参数高效的简易适配器，以及轻量级U-Net式解码器。在镜像检测和显著物体检测等多任务上的初步实验表明，SAM3-UNet优于先前的SAM2-UNet及其他先进方法，且在批量大小为12时，训练期间所需显存不足6 GB。代码已公开于https://github.com/WZH0120/SAM3-UNet。
原文摘要 · Abstract (English)
In this paper, we introduce SAM3-UNet, a simplified variant of Segment Anything Model 3 (SAM3), designed to adapt SAM3 for downstream tasks at a low cost. Our SAM3-UNet consists of three components: a SAM3 image encoder, a simple adapter for parameter-efficient fine-tuning, and a lightweight U-Net-style decoder. Preliminary experiments on multiple tasks, such as mirror detection and salient object detection, demonstrate that the proposed SAM3-UNet outperforms the prior SAM2-UNet and other state-of-the-art methods, while requiring less than 6 GB of GPU memory during training with a batch size of 12. The code is publicly available at https://github.com/WZH0120/SAM3-UNet.
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。