Hypercorrelation Squeeze for Few-Shot Segmentation

by   Juhong Min, et al.

Few-shot semantic segmentation aims at learning to segment a target object from a query image using only a few annotated support images of the target class. This challenging task requires to understand diverse levels of visual cues and analyze fine-grained correspondence relations between the query and the support images. To address the problem, we propose Hypercorrelation Squeeze Networks (HSNet) that leverages multi-level feature correlation and efficient 4D convolutions. It extracts diverse features from different levels of intermediate convolutional layers and constructs a collection of 4D correlation tensors, i.e., hypercorrelations. Using efficient center-pivot 4D convolutions in a pyramidal architecture, the method gradually squeezes high-level semantic and low-level geometric cues of the hypercorrelation into precise segmentation masks in coarse-to-fine manner. The significant performance improvements on standard few-shot segmentation benchmarks of PASCAL-5i, COCO-20i, and FSS-1000 verify the efficacy of the proposed method.



page 7

page 15

page 16

page 17

page 18

page 19

page 20

page 21


Uncertainty-Aware Semi-Supervised Few Shot Segmentation

Few shot segmentation (FSS) aims to learn pixel-level classification of ...

A New Local Transformation Module for Few-shot Segmentation

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

HMFS: Hybrid Masking for Few-Shot Segmentation

We study few-shot semantic segmentation that aims to segment a target ob...

BiOpt: Bi-Level Optimization for Few-Shot Segmentation

Few-shot segmentation is a challenging task that aims to segment objects...

Few-shot Segmentation with Optimal Transport Matching and Message Flow

We address the challenging task of few-shot segmentation in this work. I...

PFENet++: Boosting Few-shot Semantic Segmentation with the Noise-filtered Context-aware Prior Mask

In this work, we revisit the prior mask guidance proposed in "Prior Guid...

Improved Few-shot Segmentation by Redefinition of the Roles of Multi-level CNN Features

This study is concerned with few-shot segmentation, i.e., segmenting the...

Code Repositories


Official PyTorch Implementation of Hypercorrelation Squeeze for Few-Shot Segmentation, ICCV 2021

view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.