Year: 2016
Type: conference-paper
Abstract: Attributes possess appealing properties and benefit many computer vision problems, such as object recognition, learning with humans in the loop, and image retrieval. Whereas the existing work mainly pursues utilizing attributes for various computer vision problems, we contend that the most basic problem-how to accurately and robustly detect attributes from images-has been left under explored. Especially, the existing work rarely explicitly tackles the need that attribute detectors should generalize well across different categories, including those previously unseen. Noting that this is analogous to the objective of multi-source domain generalization, if we treat each category as a domain, we provide a novel perspective to attribute detection and propose to gear the techniques in multi-source domain generalization for the purpose of learning cross-category generalizable attribute detectors. We validate our understanding and approach with extensive experiments on four challenging datasets and three different problems.
DOI: 10.1109/cvpr.2016.17
Authors: Chuang Gan, Tianbao Yang, Boqing Gong
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Awards: CRII: III: Scaling up Distance Metric Learning for Large-scale Ultrahigh-dimensional Data, G325743107, G4886626501, CRII: RI: Multi-Source Domain Generalization Approaches to Visual Attribute Detection, 通讯、密码及量子信息之复杂性问题研究, G7219872841, BIGDATA: F: New Algorithms of Online Machine Learning for Big Data, G8514270459, G8623030917
OpenAlex ID: W2346746376
