RI: Medium: Creating Knowledge with All-Novel-Class Computer Vision
RI: Medium: Creating Knowledge with All-Novel-Class Computer Vision
批准号:
2106825
负责人:
David Forsyth
金额:
$120.0万
依托单位国家:
美国
项目类别:
Continuing Grant
财政年份:
2021
资助国家:
美国
项目状态:
未结题
起止时间:
2021-09-01 至 2025-08-31
中文摘要
点击翻译按钮获取中文摘要
英文摘要
Computer vision methods have had very high impact on science and industry, but this impact has been confined to cases where there is access to very large quantities of labelled data (i.e., objects are identified in the image), which have either been published, collected or purchased. This research will study computer vision methods that operate in areas where there are very little labelled data. This project builds on the natural model of the way humans and animals learn to label images. One core research goal is an object detection procedure that can be trained with all category data — there will be a small number of examples each from a large number of categories. Another core goal is a learning procedure that can share training examples across categories widely and effectively without explicit linking of the categories. A third core goal is linking learning of early vision tasks — for example, recovering shading and lighting from an image — to learning of classification and detection tasks, so that both tasks can be learned with very little labelled data. Successful completion of this research will unify apparently disparate areas of computer vision, by linking early vision and categorization directly, and will create novel methods for improving categorization performance in difficult circumstances. Furthermore, successful completion of this research will unlock many real-world applications that need all category methods. The all-novel-class problem occurs where there are a small number of examples each from a large number of classes and no class has many examples. This project addresses the all-novel-class issue by sharing of various kinds of information during training. Specifically, three kinds of sharing principles will be studied. The first is a cell consistency principle that uses a geometric and probabilistic analysis of class boundaries driven by feature generation to produce improvements in classification, by requiring that the cells in feature space associated with the similar classes. Second, a label consistency principle uses probabilistic reasoning to impute labels and confidence weights for unlabeled examples. Label consistency can be applied extensively, from category labels for individual examples to superclass labels that identify classes over which sharing will be helpful. Finally, a physical consistency principle requires that inferences from images are consistent with simple physics laws; this principle allows researchers to impute missing annotations for early vision data and links high level classes to early vision through an attribute theory.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
期刊论文(51)
专著(0)
科研奖励(0)
会议论文
登录
查看更多内容
DOI:
10.48550/arxiv.2210.09496
发表时间:
2022-10
期刊:
ArXiv
影响因子:
--
作者:
[Kai Yan;A. Schwing;Yu-Xiong Wang]
通讯作者:
Kai Yan;A. Schwing;Yu-Xiong Wang
DOI:
10.48550/arxiv.2210.08001
发表时间:
2022-10
期刊:
ArXiv
影响因子:
--
作者:
[Renan A. Rojas-Gomez;Teck-Yian Lim;A. Schwing;M. Do;Raymond A. Yeh]
通讯作者:
Renan A. Rojas-Gomez;Teck-Yian Lim;A. Schwing;M. Do;Raymond A. Yeh
SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generation; CVPR; 2023
SDFusion:多模态 3D 形状完成、重建和生成;
DOI:
--
发表时间:
2023
期刊:
IEEE Conference on Computer Vision and Pattern Recognition
影响因子:
--
作者:
[Y.-C. Cheng, H.-Y. Lee, S. Tulyakov, A.G. Schwing, L. Gui]
通讯作者:
L. Gui
DOI:
10.48550/arxiv.2206.05259
发表时间:
2022-06
期刊:
ArXiv
影响因子:
--
作者:
[Yuanyi Zhong;Haoran Tang;Jun-Kun Chen;Jian Peng;Yu-Xiong Wang]
通讯作者:
Yuanyi Zhong;Haoran Tang;Jun-Kun Chen;Jian Peng;Yu-Xiong Wang
DOI:
--
发表时间:
2021-06
期刊:
ArXiv
影响因子:
--
作者:
[Zhipeng Bao;M. Hebert;Yu-Xiong Wang]
通讯作者:
Zhipeng Bao;M. Hebert;Yu-Xiong Wang
共 40 条
Collaborative Research: Computational Behavioral Science: Modeling, Analysis, and Visualization of Social and Communicative Behavior
-
批准号:1029035
-
项目类别:Continuing Grant
-
资助金额:$150.0万
-
财政年份:2010
-
负责人:David Forsyth
-
依托单位:
RI: Small: Exploiting Geometric and Illumination Context in Indoor Scenes
-
批准号:0916014
-
项目类别:Standard Grant
-
资助金额:$45.0万
-
财政年份:2009
-
负责人:David Forsyth
-
依托单位:
INT2-Medium: Understanding the meaning of images
-
批准号:0803603
-
项目类别:Standard Grant
-
资助金额:$55.0万
-
财政年份:2008
-
负责人:David Forsyth
-
依托单位:
Interpreting Human Behaviour in Video using FSA's and Object Context
-
批准号:0534837
-
项目类别:Continuing Grant
-
资助金额:$0.0万
-
财政年份:2006
-
负责人:David Forsyth
-
依托单位:
Finding and Tracking People from the Bottom Up
-
批准号:0098682
-
项目类别:Continuing Grant
-
资助金额:$25.0万
-
财政年份:2001
-
负责人:David Forsyth
-
依托单位:
Purchase of a Molecular Modeling System
-
批准号:9974642
-
项目类别:Standard Grant
-
资助金额:$8.4万
-
财政年份:1999
-
负责人:David Forsyth
-
依托单位:
SGER: MCMC Algorithms for Object Recognition
-
批准号:9979201
-
项目类别:Standard Grant
-
资助金额:$5.0万
-
财政年份:1999
-
负责人:David Forsyth
-
依托单位:
A Spiral Approach to Chemical Concepts Using GC/MS
-
批准号:9850580
-
项目类别:Standard Grant
-
资助金额:$3.45万
-
财政年份:1998
-
负责人:David Forsyth
-
依托单位:
Workshop on Shape, Contour and Grouping
-
批准号:9712426
-
项目类别:Standard Grant
-
资助金额:$1.0万
-
财政年份:1997
-
负责人:David Forsyth
-
依托单位:
Recognising curved surfaces from their outlines
-
批准号:9596025
-
项目类别:Continuing Grant
-
资助金额:$2.69万
-
财政年份:1994
-
负责人:David Forsyth
-
依托单位:
Modeling and Recognizing Curved Surfaces from Image Outlines
-
批准号:9596047
-
项目类别:Continuing Grant
-
资助金额:$3.21万
-
财政年份:1994
-
负责人:David Forsyth
-
依托单位:
NSF Young Investigator
-
批准号:9596091
-
项目类别:Continuing Grant
-
资助金额:$17.46万
-
财政年份:1994
-
负责人:David Forsyth
-
依托单位:
Recognising curved surfaces from their outlines
-
批准号:9202129
-
项目类别:Continuing Grant
-
资助金额:$2.88万
-
财政年份:1993
-
负责人:David Forsyth
-
依托单位:
A Workshop on the Application of Invariance in Computer Vision; October 10-14, 1993; Azores
-
批准号:9311050
-
项目类别:Standard Grant
-
资助金额:$2.9万
-
财政年份:1993
-
负责人:David Forsyth
-
依托单位:
Modeling and Recognizing Curved Surfaces from Image Outlines
-
批准号:9209729
-
项目类别:Continuing Grant
-
资助金额:$10.0万
-
财政年份:1992
-
负责人:David Forsyth
-
依托单位:
NSF Young Investigator
-
批准号:9257298
-
项目类别:Continuing Grant
-
资助金额:$15.4万
-
财政年份:1992
-
负责人:David Forsyth
-
依托单位:
NMR Isotope Shifts and Alkyl Interactions (Chemistry)
-
批准号:8211125
-
项目类别:Continuing grant
-
资助金额:$0.0万
-
财政年份:1983
-
负责人:David Forsyth
-
依托单位:
海外基金