Adaptive Prototype Learning and Allocation for Few-Shot Segmentation

04/05/2021
by   Gen Li, et al.
0

Prototype learning is extensively used for few-shot segmentation. Typically, a single prototype is obtained from the support feature by averaging the global object information. However, using one prototype to represent all the information may lead to ambiguities. In this paper, we propose two novel modules, named superpixel-guided clustering (SGC) and guided prototype allocation (GPA), for multiple prototype extraction and allocation. Specifically, SGC is a parameter-free and training-free approach, which extracts more representative prototypes by aggregating similar feature vectors, while GPA is able to select matched prototypes to provide more accurate guidance. By integrating the SGC and GPA together, we propose the Adaptive Superpixel-guided Network (ASGNet), which is a lightweight model and adapts to object scale and shape variation. In addition, our network can easily generalize to k-shot segmentation with substantial improvement and no additional computational cost. In particular, our evaluations on COCO demonstrate that ASGNet surpasses the state-of-the-art method by 5 segmentation.

READ FULL TEXT

page 1

page 2

page 3

page 4

page 5

page 7

page 9

page 11

research
06/20/2022

MSANet: Multi-Similarity and Attention Guidance for Boosting Few-Shot Segmentation

Few-shot segmentation aims to segment unseen-class objects given only a ...
research
03/30/2021

Self-Guided and Cross-Guided Learning for Few-Shot Segmentation

Few-shot segmentation has been attracting a lot of attention due to its ...
research
09/16/2021

Few-Shot Object Detection by Attending to Per-Sample-Prototype

Few-shot object detection aims to detect instances of specific categorie...
research
10/03/2022

Few-Shot Segmentation via Rich Prototype Generation and Recurrent Prediction Enhancement

Prototype learning and decoder construction are the keys for few-shot se...
research
02/10/2020

Prototype Refinement Network for Few-Shot Segmentation

Few-shot segmentation targets to segment new classes with few annotated ...
research
11/15/2022

A Low-Shot Object Counting Network With Iterative Prototype Adaptation

We consider low-shot counting of arbitrary semantic categories in the im...
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 ...

Please sign up or login with your details

Forgot password? Click here to reset