Class Representative Learning for Zero-shot Learning Using Purely Visual Data
نویسندگان
چکیده
منابع مشابه
Class label autoencoder for zero-shot learning
Existing zero-shot learning (ZSL) methods usually learn a projection function between a feature space and a semantic embedding space(text or attribute space) in the training seen classes or testing unseen classes. However, the projection function cannot be used between the feature space and multi-semantic embedding spaces, which have the diversity characteristic for describing the different sem...
متن کاملVisual Abstraction for Zero-Shot Learning
Zero-shot learning (ZSL) [3, 1] involves training models for visual concepts without requiring any training images. Recent work utilizes textual descriptions (e.g., attributes) for ZSL. This works well for categories that are easily describable, but it is unclear how to extend this work to ones that are not. For example, trying to describe the concept of two people dancing with each other (e.g....
متن کاملZero-Shot Learning via Visual Abstraction
One of the main challenges in learning fine-grained visual categories is gathering training images. Recent work in Zero-Shot Learning (ZSL) circumvents this challenge by describing categories via attributes or text. However, not all visual concepts, e.g ., two people dancing, are easily amenable to such descriptions. In this paper, we propose a new modality for ZSL using visual abstraction to l...
متن کاملZero-Shot Learning via Revealing Data Distribution
This paper presents a method of zero-shot learning (ZSL) which poses ZSL as the missing data problem, rather than the missing label problem. Specifically, most existing ZSL methods focus on learning mapping functions from the image feature space to the label embedding space. Whereas, the proposed method explores a simple yet effective transductive framework in the reverse way – our method estim...
متن کاملMax-Margin Zero-Shot Learning for Multi-class Classification
Due to the dramatic expanse of data categories and the lack of labeled instances, zero-shot learning, which transfers knowledge from observed classes to recognize unseen classes, has started drawing a lot of attention from the research community. In this paper, we propose a semi-supervised max-margin learning framework that integrates the semisupervised classification problem over observed clas...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: SN Computer Science
سال: 2021
ISSN: 2662-995X,2661-8907
DOI: 10.1007/s42979-021-00648-y