paper-with-me

Papers

Synthesized Classifiers for Zero-Shot Learning

2016-03-02 · CVPR 2016 6 · Soravit Changpinyo, Wei-Lun Chao, Boqing Gong, Fei Sha

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.

📄 PDF Abstract BibTeX arXiv:1603.00550

Code (2)

JudyYe/zero-shot-gcn tf
ruotianluo/zsl-gcn-pth pytorch

Tasks

ObjectZero-Shot Learning

Similar Papers 제목 키워드 기반

Sketch-a-Classifier: Sketch-based Photo Classifier Generation

2018-04-30 · CVPR 2018 6 · Conghui Hu, Da Li, Yi-Zhe Song, Tao Xiang 외

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 Learning

End-to-end Generative Zero-shot Learning via Few-shot Learning

2021-02-08 · Georgios Chochlakis, Efthymios Georgiou, Alexandros Potamianos

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 Learning

Make an Omelette with Breaking Eggs: Zero-Shot Learning for Novel Attribute Synthesis

2021-11-28 · Yu-Hsuan Li, Tzu-Yin Chao, Ching-Chun Huang, Pin-Yu Chen 외

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 Learning

Zero-Shot Transfer Learning with Synthesized Data for Multi-Domain Dialogue State Tracking

2020-05-02 · ACL 2020 6 · Giovanni Campagna, Agata Foryciarz, Mehrad Moradshahi, Monica S. Lam

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+1

Gradient Matching Generative Networks for Zero-Shot Learning

2019-06-01 · CVPR 2019 6 · Mert Bulent Sariyildiz, Ramazan Gokberk Cinbis

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