无需重新训练，更多增益：利用扩散模型升级骨干网络以实现像素级与弱监督少样本分割
No Re-Train, More Gain: Upgrading Backbones with Diffusion model for Pixel-Wise and Weakly-Supervised Few-Shot Segmentation
AI总结：
本文提出DiffUp框架，将少样本分割建模为条件扩散生成问题，通过骨干无关特征变换、多粒度先验调制和不确定性感知融合，统一解决骨干升级、多类型标注和不同标注数量三大挑战，显著提升灵活性与准确性。
摘要：
少样本分割（FSS）旨在仅使用少量带标注图像来分割新类别。尽管在像素级支持标注下已取得可观进展，当前FSS方法仍面临三个问题：在不重新训练的情况下升级骨干网络缺乏灵活性，无法统一处理各种类型的标注（例如涂鸦、边界框、掩码和文本），以及难以适应不同的标注数量。为同时解决这些问题，我们提出DiffUp，这是一个新颖的框架，将FSS任务概念化为使用扩散过程的条件生成问题。针对第一个问题，我们引入了一个与骨干网络无关的特征变换模块，将不同的分割线索转换为统一的粗略先验，从而无需重新训练即可无缝升级骨干网络。针对第二个问题，由于来自不同标注类型（涂鸦、边界框、掩码和文本）的变换先验具有不同的粒度，我们将这些多粒度变换先验概念化为类似于扩散模型不同步骤中的噪声中间状态。这通过一个自条件调制块与一个双级质量调制分支相结合来实现。针对第三个问题，我们引入了一个不确定性感知的信息融合模块，以协调零样本、单样本和多样本场景之间的差异性。通过严格的基准测试评估，DiffUp在灵活性和准确性方面显著优于现有的FSS模型。
英文摘要：
Few-Shot Segmentation (FSS) aims to segment novel classes using only a few annotated images. Despite considerable progress under pixel-wise support annotation, current FSS methods still face three issues: the inflexibility of backbone upgrade without re-training, the inability to uniformly handle various types of annotations (e.g., scribble, bounding box, mask, and text), and the difficulty in accommodating different annotation quantity. To address these issues simultaneously, we propose DiffUp, a novel framework that conceptualizes the FSS task as a conditional generative problem using a diffusion process. For the first issue, we introduce a backbone-agnostic feature transformation module that converts different segmentation cues into unified coarse priors, facilitating seamless backbone upgrade without re-training. For the second issue, due to the varying granularity of transformed priors from diverse annotation types (scribble, bounding box, mask, and text), we conceptualize these multi-granular transformed priors as analogous to noisy intermediates at different steps of a diffusion model. This is implemented via a self-conditioned modulation block coupled with a dual-level quality modulation branch. For the third issue, we incorporate an uncertainty-aware information fusion module to harmonize the variability across zero-shot, one-shot, and many-shot scenarios. Evaluated through rigorous benchmarks, DiffUp significantly outperforms existing FSS models in terms of flexibility and accuracy.
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。
