InstaBoost: Boosting Instance Segmentation via Probability Map Guided Copy-Pasting

08/21/2019
by   Hao-Shu Fang, et al.
2

Instance segmentation requires a large number of training samples to achieve satisfactory performance and benefits from proper data augmentation. To enlarge the training set and increase the diversity, previous methods have investigated using data annotation from other domain (e.g. bbox, point) in a weakly supervised mechanism. In this paper, we present a simple, efficient and effective method to augment the training set using the existing instance mask annotations. Exploiting the pixel redundancy of the background, we are able to improve the performance of Mask R-CNN for 1.7 mAP on COCO dataset and 3.3 mAP on Pascal VOC dataset by simply introducing random jittering to objects. Furthermore, we propose a location probability map based approach to explore the feasible locations that objects can be placed based on local appearance similarity. With the guidance of such map, we boost the performance of R101-Mask R-CNN on instance segmentation from 35.7 mAP to 37.9 mAP without modifying the backbone or network structure. Our method is simple to implement and does not increase the computational complexity. It can be integrated into the training pipeline of any instance segmentation model without affecting the training and inference efficiency. Our code and models have been released at https://github.com/GothicAi/InstaBoost

READ FULL TEXT

page 1

page 3

page 4

page 5

page 6

research
04/04/2021

Weakly-supervised Instance Segmentation via Class-agnostic Learning with Salient Images

Humans have a strong class-agnostic object segmentation ability and can ...
research
09/02/2023

Soil Image Segmentation Based on Mask R-CNN

The complex background in the soil image collected in the field natural ...
research
09/28/2022

Strong Instance Segmentation Pipeline for MMSports Challenge

The goal of ACM MMSports2022 DeepSportRadar Instance Segmentation Challe...
research
04/03/2021

Recursively Refined R-CNN: Instance Segmentation with Self-RoI Rebalancing

Within the field of instance segmentation, most of the state-of-the-art ...
research
10/02/2020

DecAug: Augmenting HOI Detection via Decomposition

Human-object interaction (HOI) detection requires a large amount of anno...
research
01/26/2018

Generating Instance Segmentation Annotation by Geometry-guided GAN

Instance segmentation is a problem of significance in computer vision. H...
research
03/16/2020

TACO: Trash Annotations in Context for Litter Detection

TACO is an open image dataset for litter detection and segmentation, whi...

Please sign up or login with your details

Forgot password? Click here to reset