UINO-FSS: Unifying Representation Learning and Few-shot Segmentation via Hierarchical Distillation and Mamba-HyperCorrelation.

Few-shot semantic segmentation has attracted growing interest for its ability to generalize to novel object categories using only a few annotated samples. To address data scarcity, recent methods incorporate multiple foundation models to improve feature transferability and segmentation performance. However, they often rely on dual-branch architectures that combine pretrained encoders to leverage complementary strengths, a design that limits flexibility and efficiency. This raises a fundamental question: "can we build a unified model that integrates knowledge from different foundation architectures?" Achieving this is, however, challenging due to the misalignment between class-agnostic segmentation capabilities and fine-grained discriminative representations. To this end, we present UINO-FSS (pronounced /juː'aɪnǝʊ/), a novel framework built on the key observation that early-stage DINOv2 features exhibit distribution consistency with SAM's output embeddings. This consistency enables the integration of both models' knowledge into a single-encoder architecture via coarse-to-fine multimodal distillation. In particular, our segmenter consists of three core components: a bottleneck adapter for embedding alignment, a meta-visual prompt generator that leverages dense similarity volumes and semantic embeddings, and a mask decoder. Using hierarchical cross-model distillation, we effectively transfer SAM's knowledge into the segmenter, further enhanced by Mamba-based 4D correlation mining on support-query pairs. Extensive experiments show that UINO-FSS achieves new state-of-the-art results on COCO-20i under the 1-shot setting, with an mIoU of 64.5% (+2.2%), while also delivering competitive performance on PASCAL-5i.