Ridge Regression, Hubness, and Zero-Shot Learning
This paper discusses the effect of hubness in zero-shot learning, when ridge regression is used to find a mapping between the example space to the label space. Contrary to the existing approach, which attempts to find a mapping from the example space to the label space, we show that mapping labels into the example space is desirable to suppress the emergence of hubs in the subsequent nearest neighbor search step. Assuming a simple data model, we prove that the proposed approach indeed reduces hubness. This was verified empirically on the tasks of bilingual lexicon extraction and image labeling: hubness was reduced with both of these tasks and the accuracy was improved accordingly.
Code (0)
등록된 구현이 없습니다.
Tasks
regressionZero-Shot LearningSimilar Papers 제목 키워드 기반
Mitigating the Hubness Problem for Zero-Shot Learning of 3D Objects
The development of advanced 3D sensors has enabled many objects to be captured in the wild at a large scale, and a 3D object recognition system may therefore encounter many objects for which the system has received no tr…
3D Object RecognitionGeneralized Zero-Shot LearningObject RecognitionZero-Shot LearningHubness and Pollution: Delving into Cross-Space Mapping for Zero-Shot Learning
Adaptive Adjustment with Semantic Feature Space for Zero-Shot Recognition
In most recent years, zero-shot recognition (ZSR) has gained increasing attention in machine learning and image processing fields. It aims at recognizing unseen class instances with knowledge transferred from seen classe…
Zero-Shot LearningHubs and Hyperspheres: Reducing Hubness and Improving Transductive Few-shot Learning with Hyperspherical Embeddings
Distance-based classification is frequently used in transductive few-shot learning (FSL). However, due to the high-dimensionality of image representations, FSL classifiers are prone to suffer from the hubness problem, wh…
Few-Shot LearningSemantically Aligned Bias Reducing Zero Shot Learning
Zero shot learning (ZSL) aims to recognize unseen classes by exploiting semantic relationships between seen and unseen classes. Two major problems faced by ZSL algorithms are the hubness problem and the bias towards the …
Zero-Shot Learning