Deep Gaussian Processes for Few-Shot Segmentation

2021-03-30 · Joakim Johnander, Johan Edstedt, Martin Danelljan, Michael Felsberg, Fahad Shahbaz Khan

Few-shot segmentation is a challenging task, requiring the extraction of a generalizable representation from only a few annotated samples, in order to segment novel query images. A common approach is to model each class with a single prototype. While conceptually simple, these methods suffer when the target appearance distribution is multi-modal or not linearly separable in feature space. To tackle this issue, we propose a few-shot learner formulation based on Gaussian process (GP) regression. Through the expressivity of the GP, our approach is capable of modeling complex appearance distributions in the deep feature space. The GP provides a principled way of capturing uncertainty, which serves as another powerful cue for the final segmentation, obtained by a CNN decoder. We further exploit the end-to-end learning capabilities of our approach to learn the output space of the GP learner, ensuring a richer encoding of the segmentation mask. We perform comprehensive experimental analysis of our few-shot learner formulation. Our approach sets a new state-of-the-art for 5-shot segmentation, with mIoU scores of 68.1 and 49.8 on PASCAL-5i and COCO-20i, respectively

📄 PDF Abstract BibTeX arXiv:2103.16549

Code (0)

등록된 구현이 없습니다.

Tasks

Decoder Gaussian Processes Segmentation

Methods 이 논문이 사용한 방법론

Gaussian Process Gaussian Processes are non-parametric models for approximating functions. They rely upon a measure of similarity between points (the kernel function) to predict the value for…

Dense Gaussian Processes for Few-Shot Segmentation

2021-10-07 · Joakim Johnander, Johan Edstedt, Michael Felsberg, Fahad Shahbaz Khan 외

Few-shot segmentation is a challenging dense prediction task, which entails segmenting a novel query image given only a small annotated support set. The key problem is thus to design a method that aggregates detailed inf…

Decoder Few-Shot Semantic Segmentation Gaussian Processes Segmentation

Learning to Learn Dense Gaussian Processes for Few-Shot Learning

2021-12-01 · NeurIPS 2021 12 · Ze Wang, Zichen Miao, XianTong Zhen, Qiang Qiu

Gaussian processes with deep neural networks demonstrate to be a strong learner for few-shot learning since they combine the strength of deep learning and kernels while being able to well capture uncertainty. However, it…

Few-Shot Learning Gaussian Processes Inductive Bias Meta-Learning+1

Distributional Gaussian Process Layers for Outlier Detection in Image Segmentation

2021-04-28 · Sebastian G. Popescu, David J. Sharp, James H. Cole, Konstantinos Kamnitsas 외

We propose a parameter efficient Bayesian layer for hierarchical convolutional Gaussian Processes that incorporates Gaussian Processes operating in Wasserstein-2 space to reliably propagate uncertainty. This directly rep…

Gaussian Processes Image Segmentation Outlier Detection Out-of-Distribution Detection+2

Learning Segmented 3D Gaussians via Efficient Feature Unprojection for Zero-shot Neural Scene Segmentation

2024-01-11 · Bin Dou, Tianyu Zhang, Zhaohui Wang, Yongjia Ma 외

Zero-shot neural scene segmentation, which reconstructs 3D neural segmentation field without manual annotations, serves as an effective way for scene understanding. However, existing models, especially the efficient 3D G…

Decoder Panoptic Segmentation Scene Segmentation Scene Understanding+4

Distributional Gaussian Processes Layers for Out-of-Distribution Detection

2022-06-27 · Sebastian G. Popescu, David J. Sharp, James H. Cole, Konstantinos Kamnitsas 외

Machine learning models deployed on medical imaging tasks must be equipped with out-of-distribution detection capabilities in order to avoid erroneous predictions. It is unsure whether out-of-distribution detection model…

Gaussian Processes Out-of-Distribution Detection Segmentation