paper-with-me

홈 › Papers

Multi-label Zero-shot Classification by Learning to Transfer from External Knowledge

2020-07-30 · He Huang, Yuanwei Chen, Wei Tang, Wenhao Zheng, Qing-Guo Chen, Yao Hu, Philip Yu

Multi-label zero-shot classification aims to predict multiple unseen class labels for an input image. It is more challenging than its single-label counterpart. On one hand, the unconstrained number of labels assigned to each image makes the model more easily overfit to those seen classes. On the other hand, there is a large semantic gap between seen and unseen classes in the existing multi-label classification datasets. To address these difficult issues, this paper introduces a novel multi-label zero-shot classification framework by learning to transfer from external knowledge. We observe that ImageNet is commonly used to pretrain the feature extractor and has a large and fine-grained label space. This motivates us to exploit it as external knowledge to bridge the seen and unseen classes and promote generalization. Specifically, we construct a knowledge graph including not only classes from the target dataset but also those from ImageNet. Since ImageNet labels are not available in the target dataset, we propose a novel PosVAE module to infer their initial states in the extended knowledge graph. Then we design a relational graph convolutional network (RGCN) to propagate information among classes and achieve knowledge transfer. Experimental results on two benchmark datasets demonstrate the effectiveness of the proposed approach.

📄 PDF Abstract BibTeX arXiv:2007.15610

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationGeneral ClassificationMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATIONTransfer Learningzero-shot-classificationZero-Shot Learning

Similar Papers 제목 키워드 기반

Multi-Label Zero-Shot Learning with Transfer-Aware Label Embedding Projection

2018-08-07 · Meng Ye, Yuhong Guo

Zero-shot learning transfers knowledge from seen classes to novel unseen classes to reduce human labor of labelling data for building new classifiers. Much effort on zero-shot learning however has focused on the standard…

image-classificationImage ClassificationMulti-Label Image ClassificationMulti-label zero-shot learning+2

Realistic Zero-Shot Cross-Lingual Transfer in Legal Topic Classification

2022-06-08 · Stratos Xenouleas, Alexia Tsoukara, Giannis Panagiotakis, Ilias Chalkidis 외

We consider zero-shot cross-lingual transfer in legal topic classification using the recent MultiEURLEX dataset. Since the original dataset contains parallel documents, which is unrealistic for zero-shot cross-lingual tr…

Cross-Lingual TransferTopic ClassificationTranslationZero-Shot Cross-Lingual Transfer

Realistic Zero-Shot Cross-Lingual Transfer in Legal Topic Classification

2022-01-16 · ACL ARR January 2022 1 · Anonymous

We consider zero-shot cross-lingual transfer in legal topic classification using the recent Multi-EURLEX dataset. Since the original dataset contains parallel documents, which is unrealistic for zero-shot cross-lingual t…

ClassificationCross-Lingual TransferTopic ClassificationTranslation+1

Zero-shot Learning and Knowledge Transfer in Music Classification and Tagging

2019-06-20 · Jeong Choi, Jongpil Lee, Jiyoung Park, Juhan Nam

Music classification and tagging is conducted through categorical supervised learning with a fixed set of labels. In principle, this cannot make predictions on unseen labels. Zero-shot learning is an approach to solve th…

ClassificationGeneral ClassificationMusic ClassificationTransfer Learning+1

Multi-label Zero-Shot Audio Classification with Temporal Attention

2024-08-31 · Duygu Dogan, Huang Xie, Toni Heittola, Tuomas Virtanen

Zero-shot learning models are capable of classifying new classes by transferring knowledge from the seen classes using auxiliary information. While most of the existing zero-shot learning methods focused on single-label …

Audio ClassificationClassificationZero-shot Audio Classificationzero-shot-classification+1