Transductive Zero-Shot Learning With Adaptive Structural Embedding
- 12 October 2017
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 29 (9) , 4116-4127
Abstract
Zero-shot learning (ZSL) endows the computer vision system with the inferential capability to recognize new categories that have never seen before. Two fundamental challenges in it are visual-semantic embedding and domain adaptation in cross-modality learning and unseen class prediction steps, respectively. This paper presents two corresponding methods named Adaptive STructural Embedding (ASTE) and Self-PAced Selective Strategy (SPASS) for both challenges. Specifically, ASTE formulates the visual-semantic interactions in a latent structural support vector machine framework by adaptively adjusting the slack variables to embody different reliablenesses among training instances. To alleviate the domain shift problem in ZSL, SPASS borrows the idea from self-paced learning by iteratively selecting the unseen instances from reliable to less reliable to gradually adapt the knowledge from the seen domain to the unseen domain. Consequently, by combining SPASS and ASTE, we present a self-paced Transductive ASTE (TASTE) method to progressively reinforce the classification capacity. Extensive experiments on three benchmark data sets (i.e., AwA, CUB, and aPY) demonstrate the superiorities of ASTE and TASTE. Furthermore, we also propose a fast training (FT) strategy to improve the efficiency of most existing ZSL methods. The FT strategy is surprisingly simple and general enough, which speeds up the training time of most existing ZSL methods by 4θicksim$300 times while holding the previous performance.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (61771329, 61472273)
This publication has 31 references indexed in Scilit:
- Evaluation of output embeddings for fine-grained image classification2015
- Relevance Preserving Projection and Ranking for Web Image Search RerankingIEEE Transactions on Image Processing, 2015
- Transductive Multi-View Zero-Shot LearningIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- How to Transfer? Zero-Shot Object Recognition via Hierarchical Transfer of Semantic Attributes2015
- Transfer Learning for Visual Categorization: A SurveyIEEE Transactions on Neural Networks and Learning Systems, 2014
- Domain Adaptation of Deformable Part-Based ModelsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Glove: Global Vectors for Word Representation2014
- Feature Learning for Image Classification Via Multiobjective Genetic ProgrammingIEEE Transactions on Neural Networks and Learning Systems, 2013
- Designing Category-Level Attributes for Discriminative Visual Recognition2013
- Domain Adaptation From Multiple Sources: A Domain-Dependent Regularization ApproachIEEE Transactions on Neural Networks and Learning Systems, 2012