Pfenet++: Boosting few-shot semantic segmentation with the noise-filtered context-aware prior mask

X Luo, Z Tian, T Zhang, B Yu… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
In this work, we revisit the prior mask guidance proposed in “Prior Guided Feature
Enrichment Network for Few-Shot Segmentation”. The prior mask serves as an indicator that …

Multi-modal prototypes for open-set semantic segmentation

Y Yang, C Ma, C Ju, Y Zhang, Y Wang - arXiv preprint arXiv:2307.02003, 2023 - arxiv.org
In semantic segmentation, adapting a visual system to novel object categories at inference
time has always been both valuable and challenging. To enable such generalization …

Layer-wise mutual information meta-learning network for few-shot segmentation

X Luo, Z Duan, A Qin, Z Tian, T Xie… - … on Neural Networks …, 2024 - ieeexplore.ieee.org
The goal of few-shot segmentation (FSS) is to segment unlabeled images belonging to
previously unseen classes using only a limited number of labeled images. The main …

Unlocking the Potential of Pre-trained Vision Transformers for Few-Shot Semantic Segmentation through Relationship Descriptors

Z Zhou, HM Xu, Y Shu, L Liu - Proceedings of the IEEE/CVF …, 2024 - openaccess.thecvf.com
The recent advent of pre-trained vision transformers has unveiled a promising property: their
inherent capability to group semantically related visual concepts. In this paper we explore to …

Visual Prompting for Generalized Few-shot Segmentation: A Multi-scale Approach

MRI Hossain, M Siam, L Sigal… - Proceedings of the IEEE …, 2024 - openaccess.thecvf.com
The emergence of attention-based transformer models has led to their extensive use in
various tasks due to their superior generalization and transfer properties. Recent research …

Dynamic Knowledge Adapter with Probabilistic Calibration for Generalized Few-Shot Semantic Segmentation

J Tong, H Zhou, Y Liu, Y Hu… - Proceedings of the IEEE …, 2024 - openaccess.thecvf.com
Abstract Generalized Few-shot Semantic Segmentation (GFSS) aims to use a few novel-
class samples to enable the model trained on base classes to have the ability to segment for …

Enrich Distill and Fuse: Generalized Few-Shot Semantic Segmentation in Remote Sensing Leveraging Foundation Model's Assistance

T Gao, W Ao, XA Wang, Y Zhao, P Ma… - Proceedings of the …, 2024 - openaccess.thecvf.com
Generalized few-shot semantic segmentation (GFSS) unifies semantic segmentation with
few-shot learning showing great potential for Earth observation tasks under data scarcity …

Multi-modal prototypes for open-world semantic segmentation

Y Yang, C Ma, C Ju, F Zhang, J Yao, Y Zhang… - International Journal of …, 2024 - Springer
In semantic segmentation, generalizing a visual system to both seen categories and novel
categories at inference time has always been practically valuable yet challenging. To enable …

Generalized Few-Shot Meets Remote Sensing: Discovering Novel Classes in Land Cover Mapping via Hybrid Semantic Segmentation Framework

Z Li, F Lu, J Zou, L Hu, H Zhang - Proceedings of the IEEE …, 2024 - openaccess.thecvf.com
Land-cover mapping is one of the vital applications in Earth observation aiming at
classifying each pixel's land-cover type of remote-sensing images. As natural and human …

DRNet: Disentanglement and recombination network for few-shot semantic segmentation

Z Chang, X Gao, N Li, H Zhou… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
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 …