Synthesized Classifiers for Zero-Shot Learning
Given semantic descriptions of object classes, zero-shot learning aims to accurately recognize objects of the unseen classes, from which no examples are available at the training stage, by associating them to the seen classes, from which labeled examples are provided. We propose to tackle this problem from the perspective of manifold learning. Our main idea is to align the semantic space that is derived from external information to the model space that concerns itself with recognizing visual features. To this end, we introduce a set of "phantom" object classes whose coordinates live in both the semantic space and the model space. Serving as bases in a dictionary, they can be optimized from labeled data such that the synthesized real object classifiers achieve optimal discriminative performance. We demonstrate superior accuracy of our approach over the state of the art on four benchmark datasets for zero-shot learning, including the full ImageNet Fall 2011 dataset with more than 20,000 unseen classes.
Code (2)
Tasks
ObjectZero-Shot LearningSimilar Papers 제목 키워드 기반
Sketch-a-Classifier: Sketch-based Photo Classifier Generation
Contemporary deep learning techniques have made image recognition a reasonably reliable technology. However training effective photo classifiers typically takes numerous examples which limits image recognition's scalabil…
Transfer LearningZero-Shot LearningEnd-to-end Generative Zero-shot Learning via Few-shot Learning
Contemporary state-of-the-art approaches to Zero-Shot Learning (ZSL) train generative nets to synthesize examples conditioned on the provided metadata. Thereafter, classifiers are trained on these synthetic data in a sup…
Few-Shot LearningZero-Shot LearningMake an Omelette with Breaking Eggs: Zero-Shot Learning for Novel Attribute Synthesis
Most of the existing algorithms for zero-shot classification problems typically rely on the attribute-based semantic relations among categories to realize the classification of novel categories without observing any of t…
AttributeClassificationzero-shot-classificationZero-Shot LearningZero-Shot Transfer Learning with Synthesized Data for Multi-Domain Dialogue State Tracking
Zero-shot transfer learning for multi-domain dialogue state tracking can allow us to handle new domains without incurring the high cost of data acquisition. This paper proposes new zero-short transfer learning technique …
Data AugmentationDialogue State TrackingMulti-domain Dialogue State TrackingTransfer Learning+1Gradient Matching Generative Networks for Zero-Shot Learning
Zero-shot learning (ZSL) is one of the most promising problems where substantial progress can potentially be achieved through unsupervised learning, due to distributional differences between supervised and zero-shot clas…
Domain AdaptationGeneral ClassificationGeneralized Zero-Shot Learning - UnseenGenerative Adversarial Network+2