Saved in:
Bibliographic Details
Main Authors: Wang, Ruiqi, Patil, Akshay Gadi, Yu, Fenggen, Zhang, Hao
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2303.11530
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916314349568000
author Wang, Ruiqi
Patil, Akshay Gadi
Yu, Fenggen
Zhang, Hao
author_facet Wang, Ruiqi
Patil, Akshay Gadi
Yu, Fenggen
Zhang, Hao
contents We introduce the first active learning (AL) model for high-accuracy instance segmentation of moveable parts from RGB images of real indoor scenes. Specifically, our goal is to obtain fully validated segmentation results by humans while minimizing manual effort. To this end, we employ a transformer that utilizes a masked-attention mechanism to supervise the active segmentation. To enhance the network tailored to moveable parts, we introduce a coarse-to-fine AL approach which first uses an object-aware masked attention and then a pose-aware one, leveraging the hierarchical nature of the problem and a correlation between moveable parts and object poses and interaction directions. When applying our AL model to 2,000 real images, we obtain fully validated moveable part segmentations with semantic labels, by only needing to manually annotate 11.45% of the images. This translates to significant (60%) time saving over manual effort required by the best non-AL model to attain the same segmentation accuracy. At last, we contribute a dataset of 2,550 real images with annotated moveable parts, demonstrating its superior quality and diversity over the best alternatives.
format Preprint
id arxiv_https___arxiv_org_abs_2303_11530
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Active Coarse-to-Fine Segmentation of Moveable Parts from Real Images
Wang, Ruiqi
Patil, Akshay Gadi
Yu, Fenggen
Zhang, Hao
Computer Vision and Pattern Recognition
We introduce the first active learning (AL) model for high-accuracy instance segmentation of moveable parts from RGB images of real indoor scenes. Specifically, our goal is to obtain fully validated segmentation results by humans while minimizing manual effort. To this end, we employ a transformer that utilizes a masked-attention mechanism to supervise the active segmentation. To enhance the network tailored to moveable parts, we introduce a coarse-to-fine AL approach which first uses an object-aware masked attention and then a pose-aware one, leveraging the hierarchical nature of the problem and a correlation between moveable parts and object poses and interaction directions. When applying our AL model to 2,000 real images, we obtain fully validated moveable part segmentations with semantic labels, by only needing to manually annotate 11.45% of the images. This translates to significant (60%) time saving over manual effort required by the best non-AL model to attain the same segmentation accuracy. At last, we contribute a dataset of 2,550 real images with annotated moveable parts, demonstrating its superior quality and diversity over the best alternatives.
title Active Coarse-to-Fine Segmentation of Moveable Parts from Real Images
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2303.11530