SAM-Aware Graph Prompt Reasoning Network for Cross-Domain Few-Shot Segmentation

SF Peng, G Sun, Y Li, H Wang, GS **e - arxiv preprint arxiv:2501.00303, 2024 - arxiv.org
The primary challenge of cross-domain few-shot segmentation (CD-FSS) is the domain
disparity between the training and inference phases, which can exist in either the input data …

Symmetrical Joint Learning Support-query Prototypes for Few-shot Segmentation

Q Li, B Sun, F **ao, Y Qi, B Bhanu - arxiv preprint arxiv:2407.19306, 2024 - arxiv.org
We propose Sym-Net, a novel framework for Few-Shot Segmentation (FSS) that addresses
the critical issue of intra-class variation by jointly learning both query and support prototypes …

Self-Supervised Image Segmentation Using Meta-Learning and Multi-Backbone Feature Fusion

MS Ajmal, G Geng, X Wang… - International journal of …, 2024 - pubmed.ncbi.nlm.nih.gov
Few-shot segmentation (FSS) aims to reduce the need for manual annotation, which is both
expensive and time-consuming. While FSS enhances model generalization to new concepts …

Adapting Informative Structures for Cross-Domain Few-Shot Segmentation

Q Fan, KQ Liu, N Liu, H Cholakkal, RM Anwer, W Li… - openreview.net
Cross-domain few-shot segmentation (CD-FSS) aims to segment objects of novel classes
under domain shifts, using only a few mask-annotated support samples. However, directly …