- Library Home /
- Search Collections /
- Open Collections /
- Browse Collections /
- UBC Theses and Dissertations /
- Where are the objects? : weakly supervised methods...
Open Collections
UBC Theses and Dissertations
UBC Theses and Dissertations
Where are the objects? : weakly supervised methods for counting, localization and segmentation Laradji, Issam
Abstract
In 2012, deep learning made a major comeback. Deep learning started breaking records in many machine learning benchmarks, especially those in the field of computer vision. By integrating deep learning, machine learning methods have became more practical for many applications like object counting, detection, or segmentation. Unfortunately, in the typical supervised learning setting, deep learning methods might require a lot of labeled data that are costly to acquire. For instance, in the case of acquiring segmentation labels, the annotator has to label each pixel in order to draw a mask over each object and get the background regions. In fact, each image in the CityScapes dataset took around 1.5 hours to label. Further, to achieve high accuracy, we might need millions of such images. In this work, we propose four weakly supervised methods. They only require labels that are cheap to collect, yet they perform well in practice. We devised an experimental setup for each proposed method. In the first setup, the model needs to learn to count objects from point annotations. In the second setup, the model needs to learn to segment objects from point annotations. In the third setup, the model needs to segment objects from image level annotations. In the final setup, the model needs to learn to detect objects using counts only. For each of these setups the proposed method achieves state-of-the-art results in its respective benchmark. Interestingly, our methods are not much worse than fully supervised methods. This is despite their training labels being significantly cheaper to acquire than for the fully supervised case. In fact, in fixing the time budget for collecting annotations, our models performed much better than fully supervised methods. This suggests that carefully designed models can effectively learn from data labeled with low human effort.
Item Metadata
Title |
Where are the objects? : weakly supervised methods for counting, localization and segmentation
|
Creator | |
Publisher |
University of British Columbia
|
Date Issued |
2020
|
Description |
In 2012, deep learning made a major comeback. Deep learning started breaking records in many machine learning benchmarks, especially those in the field of computer vision. By integrating deep learning, machine learning methods have became more practical for many applications like object counting, detection, or segmentation. Unfortunately, in the typical supervised learning setting, deep learning methods might require a lot of labeled data that are costly to acquire. For instance, in the case of acquiring segmentation labels, the annotator has to label each pixel in order to draw a mask over each object and get the background regions. In fact, each image in the CityScapes dataset took around 1.5 hours to label. Further, to achieve high accuracy, we might need millions of such images.
In this work, we propose four weakly supervised methods. They only require labels that are cheap to collect, yet they perform well in practice. We devised an experimental setup for each proposed method. In the first setup, the model needs to learn to count objects from point annotations. In the second setup, the model needs to learn to segment objects from point annotations. In the third setup, the model needs to segment objects from image level annotations. In the final setup, the model needs to learn to detect objects using counts only. For each of these setups the proposed method achieves state-of-the-art results in its respective benchmark. Interestingly, our methods are not much worse than fully supervised methods. This is despite their training labels being significantly cheaper to acquire than for the fully supervised case. In fact, in fixing the time budget for collecting annotations, our models performed much better than fully supervised methods. This suggests that carefully designed models can effectively learn from data labeled with low human effort.
|
Genre | |
Type | |
Language |
eng
|
Date Available |
2020-05-07
|
Provider |
Vancouver : University of British Columbia Library
|
Rights |
Attribution 4.0 International
|
DOI |
10.14288/1.0390386
|
URI | |
Degree | |
Program | |
Affiliation | |
Degree Grantor |
University of British Columbia
|
Graduation Date |
2020-05
|
Campus | |
Scholarly Level |
Graduate
|
Rights URI | |
Aggregated Source Repository |
DSpace
|
Item Media
Item Citations and Data
Rights
Attribution 4.0 International