Abstract
Generalized few-shot semantic segmentation (GFSS) is fundamentally limited by the coverage of novel-class appearances under scarce annotations. While diffusion models can synthesize novel-class images at scale, practical gains are often hindered by insufficient coverage and noisy supervision when masks are unavailable or unreliable. We propose Syn4Seg, a generation-enhanced GFSS framework designed to expand novel-class coverage while improving pseudo-label quality. Syn4Seg first maximizes prompt-space coverage by constructing an embedding-deduplicated prompt bank for each novel class, yielding diverse yet class-consistent synthetic images. It then performs support-guided pseudo-label estimation via a two-stage refinement that i) filters low-consistency regions to obtain high-precision seeds and ii) relabels uncertain pixels with image-adaptive prototypes that combine global (support) and local (image) statistics. Finally, we refine only boundary-band and unlabeled pixels using a constrained SAM-based update to improve contour fidelity without overwriting high-confidence interiors. Extensive experiments on PASCAL-$5^i$ and COCO-$20^i$ demonstrate consistent improvements in both 1-shot and 5-shot settings, highlighting synthetic data as a scalable path for GFSS with reliable masks and precise boundaries.
Abstract (translated)
广义小样本语义分割（GFSS）从根本上受限于稀缺标注下新类外观的覆盖范围。尽管扩散模型能够大规模合成新类图像，但当掩码不可用或不可靠时，覆盖不足和噪声监督往往制约实际效果。我们提出Syn4Seg，一个生成增强型GFSS框架，旨在扩展新类覆盖范围同时提升伪标签质量。Syn4Seg首先通过为每个新类构建嵌入去重的提示词库，最大化提示空间覆盖，生成多样且类别一致的合成图像。随后执行支持引导的伪标签估计，采用两阶段细化：i）过滤低一致性区域以获得高精度种子点；ii）利用结合全局（支持集）与局部（图像）统计的图像自适应原型，对不确定像素进行重标注。最后，仅对边界带和未标注像素执行基于约束SAM的更新，在不覆盖高置信度内部区域的前提下提升轮廓精度。在PASCAL-$5^i$和COCO-$20^i$上的大量实验表明，该方法在1-shot和5-shot设置下均实现稳定提升，凸显了合成数据作为GFSS可扩展路径的潜力，可同时保证可靠掩码与精确边界。
URL
https://arxiv.org/abs/2603.27206
