Published on Fri Jan 26 2018

SRDA: Generating Instance Segmentation Annotation Via Scanning, Reasoning And Domain Adaptation

Wenqiang Xu, Yonglu Li, Cewu Lu

We introduce a novel pipeline named SRDA to obtain large quantities of training samples with very minor effort. Our pipeline is well-suited to scenes that can be scanned, i.e. most indoor and outdoor scenarios.

0
0
0
Abstract

Instance segmentation is a problem of significance in computer vision. However, preparing annotated data for this task is extremely time-consuming and costly. By combining the advantages of 3D scanning, reasoning, and GAN-based domain adaptation techniques, we introduce a novel pipeline named SRDA to obtain large quantities of training samples with very minor effort. Our pipeline is well-suited to scenes that can be scanned, i.e. most indoor and some outdoor scenarios. To evaluate our performance, we build three representative scenes and a new dataset, with 3D models of various common objects categories and annotated real-world scene images. Extensive experiments show that our pipeline can achieve decent instance segmentation performance given very low human labor cost.

Wed Jul 21 2021
Computer Vision
S4T: Source-free domain adaptation for semantic segmentation via self-supervised selective self-training
Most modern approaches for domain adaptive semantic segmentation rely on continued access to source data during adaptation, which may be infeasible due to computational or privacy constraints. We propose Self-Supervised Selective Self-Training (S4T), a source-free adaptation method.
2
0
0
Fri Jul 09 2021
Computer Vision
Semantic Segmentation on Multiple Visual Domains
Semantic segmentation models only perform well on the domain they are trained on. datasets for training are scarce and often have a small label-spaces. A method for this is proposed for Cityscapes, SUIM and SUN RGB-D.
2
0
0
Mon Jul 02 2018
Artificial Intelligence
Semantic Segmentation with Scarce Data
Semantic segmentation is a challenging vision problem that usually necessitates the collection of large amounts of finely annotated data. We present a method to leverage coarsely annotatedData along with fine Supervision to produce better segmentation results than would be obtained when training using only the fine data.
0
0
0
Mon Jul 15 2019
Computer Vision
MaskPlus: Improving Mask Generation for Instance Segmentation
Instance segmentation is a promising yet challenging topic in computer vision. Recent approaches such as Mask R-CNN typically divide this problem into two parts -- a detection component and a mask generation branch. In this paper, we present an approach that extends Mask R- CNN with five novel optimization techniques.
0
0
0
Tue May 14 2019
Computer Vision
Budget-aware Semi-Supervised Semantic and Instance Segmentation
Methods that move towards less supervised scenarios are key for image segmentation, as dense labels demand significant human intervention. We present results for the Pascal VOC benchmark and unify weakly and semi-supervised approaches by considering the total annotation budget.
0
0
0
Thu Dec 27 2018
Computer Vision
S4-Net: Geometry-Consistent Semi-Supervised Semantic Segmentation
We show that it is possible to learn semantic segmentation from very limited amounts of manual annotations. We show that introducing geometric 3D constraints during learning is very effective, even when no manual label is available for a 3D point.
0
0
0