用双分辨率+DINOv2增强SAM2，提升分割精度
SAM2-UNeXT: An Improved High-Resolution Baseline for Adapting Foundation Models to Downstream Segmentation Tasks
- 融合DINOv2与SAM2-UNet，提升特征表达能力
- 在4个数据集上实现更优分割效果，无需复杂解码器
- 适合需要高精度分割的视觉任务研究者
近期研究揭示了将基础分割模型SAM应用于下游任务的潜力，但构建更强大且通用的编码器以进一步提升性能仍是开放挑战。本文提出SAM2-UNeXT，基于SAM2-UNet的核心思想，通过引入辅助的DINOv2编码器扩展了SAM2的表征能力。结合双分辨率策略与密集连接层，该方法在保持简洁架构的同时实现了更精准的分割，降低了对复杂解码器的依赖。在四个基准测试（包括二值图像分割、伪装目标检测、海洋动物分割和遥感显著性检测）上的大量实验表明，所提方法表现卓越。代码已开源：https://github.com/WZH0120/SAM2-UNeXT。
原文摘要 · Abstract (English)
Recent studies have highlighted the potential of adapting the Segment Anything Model (SAM) for various downstream tasks. However, constructing a more powerful and generalizable encoder to further enhance performance remains an open challenge. In this work, we propose SAM2-UNeXT, an advanced framework that builds upon the core principles of SAM2-UNet while extending the representational capacity of SAM2 through the integration of an auxiliary DINOv2 encoder. By incorporating a dual-resolution strategy and a dense glue layer, our approach enables more accurate segmentation with a simple architecture, relaxing the need for complex decoder designs. Extensive experiments conducted on four benchmarks, including dichotomous image segmentation, camouflaged object detection, marine animal segmentation, and remote sensing saliency detection, demonstrate the superior performance of our proposed method. The code is available at https://github.com/WZH0120/SAM2-UNeXT.
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。