PASCAL-5^i

PASCAL-5^i is a benchmark dataset used to evaluate few-shot semantic segmentation by providing a set of images with a limited number of labeled examples for novel classes.

Papers using PASCAL-5^i (10)

Prior Guided Feature Enrichment Network For Few-shot Segmentation2020 · 585 citesFeature Weighting And Boosting For Few-shot Segmentation2019 · 307 citesFSOD-VFM: Few-Shot Object Detection with Vision Foundation Models and Graph Diffusion2026Efficient Masked Attention Transformer For Few-shot Classification And Segmentation2025Learning Meta-class Memory For Few-shot Semantic Segmentation2021 · 129 citesCobnet: Cross Attention On Object And Background For Few-shot Segmentation2022 · 3 citesApplying Vit In Generalized Few-shot Semantic Segmentation2024Few-shot semantic segmentation via mask aggregation2022 · 2 citesWeakly Supervised Few-shot Object Segmentation using Co-Attention with Visual and Semantic Embeddings2020CobNet: Cross Attention on Object and Background for Few-Shot Segmentation2022