Few-shot semantic segmentation: a review on recent approaches
Z Chang, Y Lu, X Ran, X Gao, X Wang - Neural Computing and …, 2023 - Springer
Few-shot semantic segmentation (FSS) is a challenging task that aims to learn to segment
novel categories with only a few labeled images, and it has a wide range of real-world …
novel categories with only a few labeled images, and it has a wide range of real-world …
Space engage: Collaborative space supervision for contrastive-based semi-supervised semantic segmentation
Abstract Semi-Supervised Semantic Segmentation (S4) aims to train a segmentation model
with limited labeled images and a substantial volume of unlabeled images. To improve the …
with limited labeled images and a substantial volume of unlabeled images. To improve the …
Cracknex: a few-shot low-light crack segmentation model based on retinex theory for uav inspections
Routine visual inspections of concrete structures are imperative for upholding the safety and
integrity of critical infrastructure. Such visual inspections sometimes happen under low-light …
integrity of critical infrastructure. Such visual inspections sometimes happen under low-light …
Query-guided Prototype Evolution Network for Few-Shot Segmentation
Previous Few-Shot Segmentation (FSS) approaches exclusively utilize support features for
prototype generation, neglecting the specific requirements of the query. To address this, we …
prototype generation, neglecting the specific requirements of the query. To address this, we …
Lite-FENet: Lightweight multi-scale feature enrichment network for few-shot segmentation
Current methods for few-shot segmentation focus on extracting information from support and
query targets, however, most of these methods not only suffer from high model complexity …
query targets, however, most of these methods not only suffer from high model complexity …
DRNet: Disentanglement and recombination network for few-shot semantic segmentation
Few-shot semantic segmentation (FSS) aims to segment novel classes with only a few
annotated samples. Existing methods to FSS generally combine the annotated mask and the …
annotated samples. Existing methods to FSS generally combine the annotated mask and the …
Contrastive prototype network with prototype augmentation for few-shot classification
M Jiang, J Fan, J He, W Du, Y Wang, F Li - Information Sciences, 2025 - Elsevier
In recent years, metric-based meta-learning methods have received widespread attention
because of their effectiveness in solving few-shot classification problems. However, the …
because of their effectiveness in solving few-shot classification problems. However, the …
A novel inference paradigm based on multi-view prototypes for one-shot semantic segmentation
H Wang, G Cao, W Cao - Applied Intelligence, 2023 - Springer
One-shot semantic segmentation approaches aim to learn a meta-learning framework from
seen classes with annotated samples, which can be applied in novel classes with only one …
seen classes with annotated samples, which can be applied in novel classes with only one …
A language-guided benchmark for weakly supervised open vocabulary semantic segmentation
Increasing attention is being diverted to data-efficient problem settings like Open Vocabulary
Semantic Segmentation (OVSS) which deals with segmenting an arbitrary object that may or …
Semantic Segmentation (OVSS) which deals with segmenting an arbitrary object that may or …
Uncertainty guided semi-supervised few-shot segmentation with prototype level fusion
H Wang, C Wu, H Zhang, G Cao, W Cao - Neural Networks, 2025 - Elsevier
Abstract Few-Shot Semantic Segmentation (FSS) aims to tackle the challenge of segmenting
novel categories with limited annotated data. However, given the diversity among support …
novel categories with limited annotated data. However, given the diversity among support …