Task-Adaptive Feature Transformer for Few-Shot Segmentation

10/22/2020
by   Jun Seo, et al.
0

Few-shot learning allows machines to classify novel classes using only a few labeled samples. Recently, few-shot segmentation aiming at semantic segmentation on low sample data has also seen great interest. In this paper, we propose a learnable module for few-shot segmentation, the task-adaptive feature transformer (TAFT). TAFT linearly transforms task-specific high-level features to a set of task-agnostic features well-suited to the segmentation job. Using this task-conditioned feature transformation, the model is shown to effectively utilize the semantic information in novel classes to generate tight segmentation masks. The proposed TAFT module can be easily plugged into existing semantic segmentation algorithms to achieve few-shot segmentation capability with only a few added parameters. We combine TAFT with Deeplab V3+, a well-known segmentation architecture; experiments on the PASCAL-5^i dataset confirm that this combination successfully adds few-shot learning capability to the segmentation algorithm, achieving the state-of-the-art few-shot segmentation performance in some key representative cases.

READ FULL TEXT

page 3

page 5

page 11

page 13

page 14

page 15

research
02/14/2022

Task-Adaptive Feature Transformer with Semantic Enrichment for Few-Shot Segmentation

Few-shot learning allows machines to classify novel classes using only a...
research
11/02/2022

tSF: Transformer-based Semantic Filter for Few-Shot Learning

Few-Shot Learning (FSL) alleviates the data shortage challenge via embed...
research
03/18/2020

CAFENet: Class-Agnostic Few-Shot Edge Detection Network

We tackle a novel few-shot learning challenge, which we call few-shot se...
research
07/30/2022

Doubly Deformable Aggregation of Covariance Matrices for Few-shot Segmentation

Training semantic segmentation models with few annotated samples has gre...
research
04/13/2023

Task Adaptive Feature Transformation for One-Shot Learning

We introduce a simple non-linear embedding adaptation layer, which is fi...
research
10/15/2022

Prediction Calibration for Generalized Few-shot Semantic Segmentation

Generalized Few-shot Semantic Segmentation (GFSS) aims to segment each i...
research
10/14/2019

A New Local Transformation Module for Few-shot Segmentation

Few-shot segmentation segments object regions of new classes with a few ...

Please sign up or login with your details

Forgot password? Click here to reset