SG-One: Similarity Guidance Network for One-Shot Semantic Segmentation

10/22/2018
by   Xiaolin Zhang, et al.
46

One-shot semantic segmentation poses a challenging task of recognizing the object regions from unseen categories with only one annotated example as supervision. In this paper, we propose a simple yet effective Similarity Guidance network to tackle the One-shot (SG-One) segmentation problem. We aim at predicting the segmentation mask of a query image with the reference to one densely labeled support image. To obtain the robust representative feature of the support image, we firstly propose a masked average pooling strategy for producing the guidance features using only the pixels belonging to the support image. We then leverage the cosine similarity to build the relationship between the guidance features and features of pixels from the query image. In this way, the possibilities embedded in the produced similarity maps can be adopted to guide the process of segmenting objects. Furthermore, our SG-One is a unified framework which can efficiently process both support and query images within one network and be learned in an end-to-end manner. We conduct extensive experiments on Pascal VOC 2012. In particular, our SG-One achieves the mIoU score of 46.3

READ FULL TEXT

page 3

page 7

research
03/17/2022

Multi-similarity based Hyperrelation Network for few-shot segmentation

Few-shot semantic segmentation aims at recognizing the object regions of...
research
04/22/2022

Dynamic Prototype Convolution Network for Few-Shot Semantic Segmentation

The key challenge for few-shot semantic segmentation (FSS) is how to tai...
research
08/11/2021

Few-Shot Segmentation with Global and Local Contrastive Learning

In this work, we address the challenging task of few-shot segmentation. ...
research
02/22/2021

Semantically Meaningful Class Prototype Learning for One-Shot Image Semantic Segmentation

One-shot semantic image segmentation aims to segment the object regions ...
research
09/28/2019

Feature Weighting and Boosting for Few-Shot Segmentation

This paper is about few-shot segmentation of foreground objects in image...
research
04/21/2022

Beyond the Prototype: Divide-and-conquer Proxies for Few-shot Segmentation

Few-shot segmentation, which aims to segment unseen-class objects given ...
research
01/02/2019

Visualizing Deep Similarity Networks

For convolutional neural network models that optimize an image embedding...

Please sign up or login with your details

Forgot password? Click here to reset