A Novel Benchmark for Few-Shot Semantic Segmentation in the Era of Foundation Models

arXiv:2401.11311v2 Announce Type: replace
Abstract: In recent years, the rapid evolution of computer vision has seen the emergence of various foundation models, each tailored to specific data types and tasks. In this study, we explore the adaptation of these models for few-shot semantic segmentation. Specifically, we conduct a comprehensive comparative analysis of four prominent foundation models: DINO V2, Segment Anything, CLIP, Masked AutoEncoders, and of a straightforward ResNet50 pre-trained on the COCO dataset. We also include 5 adaptation methods, ranging …

abstract arxiv benchmark computer computer vision cs.cv data emergence evolution explore few-shot foundation novel segmentation semantic study tasks type types vision