2017 IEEE International Conference on Computer Vision (ICCV) 2017
DOI: 10.1109/iccv.2017.146
|View full text |Cite
|
Sign up to set email alerts
|

Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection

Abstract: A major impediment in rapidly deploying object detection models for instance detection is the lack of large annotated datasets. For example, finding a large labeled dataset containing instances in a particular kitchen is unlikely. Each new environment with new instances requires expensive data collection and annotation. In this paper, we propose a simple approach to generate large annotated instance datasets with minimal effort. Our key insight is that ensuring only patch-level realism provides enough training… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

7
540
0
4

Year Published

2018
2018
2019
2019

Publication Types

Select...
5
1

Relationship

0
6

Authors

Journals

citations
Cited by 589 publications
(551 citation statements)
references
References 62 publications
7
540
0
4
Order By: Relevance
“…A similar problem is also pointed out in previous work [10]: they had objects for which it is difficult to extract foreground mask by thresholding of the depth image, in particular with transparent objects such as Cola Bottle. To overcome this difficulty, they trained a small convolutional neural network (ConvNet) model [21] using the mask acquired from thresholding of the depth image as the ground truth.…”
Section: Image Synthesis For Learning Instance Occlusion Segmentatsupporting
confidence: 57%
See 4 more Smart Citations
“…A similar problem is also pointed out in previous work [10]: they had objects for which it is difficult to extract foreground mask by thresholding of the depth image, in particular with transparent objects such as Cola Bottle. To overcome this difficulty, they trained a small convolutional neural network (ConvNet) model [21] using the mask acquired from thresholding of the depth image as the ground truth.…”
Section: Image Synthesis For Learning Instance Occlusion Segmentatsupporting
confidence: 57%
“…Above work focus on developing ways to make synthetic images closer to real images. On the other hand, it has recently been found that synthesizing only 2D instance images of objects is also effective to train detection models of object bounding boxes [9,10]. The base idea for this is that if we could generate infinite synthetic images at random and train learning model with it, the model would generalize to real images.…”
Section: B Image Synthesis For Object Detectionmentioning
confidence: 99%
See 3 more Smart Citations