Diverse Expected Gradient Active Learning for Relative Attributes
نویسندگان
چکیده
منابع مشابه
Active Learning for Image Ranking Over Relative Visual Attributes
Visual attributes are human-nameable, cross-categorical image concepts used by people everyday to describe objects. For instance, cats are “furry” while turtles are not. Some shoes are “shiny” while others are not. These human-intuitive attributes have significant uses in the computer vision field. Yet it is even more intuitive, and informative, to be able to ascribe the degree of some attribut...
متن کاملSimultaneous Active Learning of Classifiers & Attributes via Relative Feedback
Active learning provides useful tools to reduce annotation costs without compromising classifier performance. However it traditionally views the supervisor simply as a labeling machine. Recently a new interactive learning paradigm was introduced that allows the supervisor to additionally convey useful domain knowledge using attributes. The learner first conveys its belief about an actively chos...
متن کاملActive Learning for Hidden Attributes in Networks
In many networks, vertices have hidden attributes, or types, that are correlated with the networks topology. If the topology is known but these attributes are not, and if learning the attributes is costly, we need a method for choosing which vertex to query in order to learn as much as possible about the attributes of the other vertices. We assume the network is generated by a stochastic block ...
متن کاملUnsupervised Learning of Discriminative Relative Visual Attributes
Unsupervised learning of relative visual attributes is important because it is often infeasible for a human annotator to predefine and manually label all the relative attributes in large datasets. We propose a method for learning relative visual attributes given a set of images for each training class. The method is unsupervised in the sense that it does not require a set of predefined attribut...
متن کاملLearning Attributes from the Crowdsourced Relative Labels
Finding semantic attributes to describe related concepts is typically a hard problem. The commonly used attributes in most fields are designed by domain experts, which is expensive and time-consuming. In this paper we propose an efficient method to learn human comprehensible attributes with crowdsourcing. We first design an analogical interface to collect relative labels from the crowds. Then w...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Transactions on Image Processing
سال: 2014
ISSN: 1057-7149,1941-0042
DOI: 10.1109/tip.2014.2327805