Back to Search
Start Over
Imagination Based Sample Construction for Zero-Shot Learning
- Source :
- SIGIR
- Publication Year :
- 2018
- Publisher :
- ACM, 2018.
-
Abstract
- Zero-shot learning (ZSL) which aims to recognize unseen classes with no labeled training sample, efficiently tackles the problem of missing labeled data in image retrieval. Nowadays there are mainly two types of popular methods for ZSL to recognize images of unseen classes: probabilistic reasoning and feature projection. Different from these existing types of methods, we propose a new method: sample construction to deal with the problem of ZSL. Our proposed method, called Imagination Based Sample Construction (IBSC), innovatively constructs image samples of target classes in feature space by mimicking human associative cognition process. Based on an association between attribute and feature, target samples are constructed from different parts of various samples. Furthermore, dissimilarity representation is employed to select high-quality constructed samples which are used as labeled data to train a specific classifier for those unseen classes. In this way, zero-shot learning is turned into a supervised learning problem. As far as we know, it is the first work to construct samples for ZSL thus, our work is viewed as a baseline for future sample construction methods. Experiments on four benchmark datasets show the superiority of our proposed method.<br />Accepted as a short paper in ACM SIGIR 2018
- Subjects :
- FOS: Computer and information sciences
Imagination
Computer science
business.industry
Computer Vision and Pattern Recognition (cs.CV)
Feature vector
media_common.quotation_subject
05 social sciences
Supervised learning
Computer Science - Computer Vision and Pattern Recognition
Probabilistic logic
Pattern recognition
02 engineering and technology
Zero shot learning
050105 experimental psychology
0202 electrical engineering, electronic engineering, information engineering
020201 artificial intelligence & image processing
0501 psychology and cognitive sciences
Artificial intelligence
business
Image retrieval
Classifier (UML)
media_common
Subjects
Details
- Database :
- OpenAIRE
- Journal :
- The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval
- Accession number :
- edsair.doi.dedup.....f587cb185d549892a70373c41b2b6c70