Box2Mask: Box-supervised Instance Segmentation via Level-set Evolution

12/03/2022
by   Wentong Li, et al.
0

In contrast to fully supervised methods using pixel-wise mask labels, box-supervised instance segmentation takes advantage of simple box annotations, which has recently attracted increasing research attention. This paper presents a novel single-shot instance segmentation approach, namely Box2Mask, which integrates the classical level-set evolution model into deep neural network learning to achieve accurate mask prediction with only bounding box supervision. Specifically, both the input image and its deep features are employed to evolve the level-set curves implicitly, and a local consistency module based on a pixel affinity kernel is used to mine the local context and spatial relations. Two types of single-stage frameworks, i.e., CNN-based and transformer-based frameworks, are developed to empower the level-set evolution for box-supervised instance segmentation, and each framework consists of three essential components: instance-aware decoder, box-level matching assignment and level-set evolution. By minimizing the level-set energy function, the mask map of each instance can be iteratively optimized within its bounding box annotation. The experimental results on five challenging testbeds, covering general scenes, remote sensing, medical and scene text images, demonstrate the outstanding performance of our proposed Box2Mask approach for box-supervised instance segmentation. In particular, with the Swin-Transformer large backbone, our Box2Mask obtains 42.4 developed fully mask-supervised methods. The code is available at: https://github.com/LiWentomng/boxlevelset.

READ FULL TEXT

page 2

page 6

page 15

page 18

page 19

research
07/19/2022

Box-supervised Instance Segmentation with Level Set Evolution

In contrast to the fully supervised methods using pixel-wise mask labels...
research
12/21/2021

SOIT: Segmenting Objects with Instance-Aware Transformers

This paper presents an end-to-end instance segmentation framework, terme...
research
11/23/2021

Bounding Box-Free Instance Segmentation Using Semi-Supervised Learning for Generating a City-Scale Vehicle Dataset

Vehicle classification is a hot computer vision topic, with studies rang...
research
12/07/2021

Deep Level Set for Box-supervised Instance Segmentation in Aerial Images

Box-supervised instance segmentation has recently attracted lots of rese...
research
11/25/2019

Shape-aware Feature Extraction for Instance Segmentation

Modern instance segmentation approaches mainly adopt a sequential paradi...
research
12/07/2022

BoxPolyp:Boost Generalized Polyp Segmentation Using Extra Coarse Bounding Box Annotations

Accurate polyp segmentation is of great importance for colorectal cancer...
research
03/28/2023

Mask-Free Video Instance Segmentation

The recent advancement in Video Instance Segmentation (VIS) has largely ...

Please sign up or login with your details

Forgot password? Click here to reset