Asking Friendly Strangers: Non-Semantic Attribute Transfer
نویسندگان
چکیده
Attributes can be used to recognize unseen objects from a textual description. Their learning is oftentimes accomplished with a large amount of annotations, e.g. around 160k-180k, but what happens if for a given attribute, we do not have many annotations? The standard approach would be to perform transfer learning, where we use source models trained on other attributes, to learn a separate target attribute. However existing approaches only consider transfer from attributes in the same domain i.e. they perform semantic transfer between attributes that have related meaning. Instead, we propose to perform non-semantic transfer from attributes that may be in different domains, hence they have no semantic relation to the target attributes. We develop an attention-guided transfer architecture that learns how to weigh the available source attribute classifiers, and applies them to image features for the attribute name of interest, to make predictions for that attribute. We validate our approach on 272 attributes from five domains: animals, objects, scenes, shoes and textures. We show that semantically unrelated attributes provide knowledge that helps improve the accuracy of the target attribute of interest, more so than only allowing transfer from semantically related attributes.
منابع مشابه
A combination of semantic and attribute-based access control model for virtual organizations
A Virtual Organization (VO) consists of some real organizations with common interests, which aims to provide inter organizational associations to reach some common goals by sharing their resources with each other. Providing security mechanisms, and especially a suitable access control mechanism, which enforces the defined security policy is a necessary requirement in VOs. Since VO is a complex ...
متن کاملJoint Semantic and Latent Attribute Modelling for Cross-Class Transfer Learning.
A number of vision problems such as zero-shot learning and person re-identification can be considered as cross-class transfer learning problems. As mid-level semantic properties shared cross different object classes, attributes have been studied extensively for knowledge-transfer across classes. Most previous attribute learning methods focus only on human-defined/nameable semantic attributes, w...
متن کاملAutomatic Addition of Verbal Semantic Attributes to a Japanese-to-English Valency Transfer Dictionary
The effectiveness of using the semantic attributes of verbs has been shown in various kinds of natural processing systems, such as machine translation systems. The addition of an attribute value is, however, time-consuming and must be performed by hand by an expert on the attribute value. In this paper, two methods for efficiently adding verbal semantic attributes to a Japanese-to-English valen...
متن کاملCombining Language Sources and Robust Semantic Relatedness for Attribute-Based Knowledge Transfer
Knowledge transfer between object classes has been identified as an important tool for scalable recognition. However, determining which knowledge to transfer where remains a key challenge. While most approaches employ varying levels of human supervision, we follow the idea of mining linguistic knowledge bases to automatically infer transferable knowledge. In contrast to previous work, we explic...
متن کامل