Make It Up: Fake Images, Real Gains in Generalized Few-shot Semantic Segmentation
This work addresses the limited novel-class coverage in few-shot segmentation for computer vision researchers, offering a scalable synthetic data approach with improved mask quality.
Syn4Seg improves generalized few-shot semantic segmentation by using diffusion models to generate diverse synthetic images of novel classes and refining pseudo-labels via support-guided estimation and SAM-based boundary refinement, achieving consistent gains on PASCAL-5^i and COCO-20^i in 1-shot and 5-shot settings.
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.