Zero-Shot Domain Adaptation via Kernel Regression on the Grassmannian

Abstract

Most visual recognition methods implicitly assume the data distribution remains unchanged from training to testing. However, in practice domain shift often exists, where real-world factors such as lighting and sensor type change between train and test, and classifiers do not generalise from source to target domains. It is impractical to train separate models for all possible situations because collecting and labelling the data is expensive. Domain adaptation algorithms aim to ameliorate domain shift, allowing a model trained on a source to perform well on a different target domain. However, even for the setting of unsupervised domain adaptation, where the target domain is unlabelled, collecting data for every possible target domain is still costly. In this paper, we propose a new domain adaptation method that has no need to access either data or labels of the target domain when it can be described by a parametrised vector and there exits several related source domains within the same parametric space. It greatly reduces the burden of data collection and annotation, and our experiments show some promising results.

Accepted to BMVC 2015 Workshop on Differential Geometry in Computer Vision (DIFF-CV)

References in corpus (3)

• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
• Return of the Devil in the Details: Delving Deep into Convolutional Nets
• Polynomial Regression on Riemannian Manifolds

Cited by in corpus (7)

• Joint Geometrical and Statistical Alignment for Visual Domain Adaptation
• Zero-shot Domain Adaptation without Domain Semantic Descriptors
• Generalized Zero-Shot Domain Adaptation via Coupled Conditional Variational Autoencoders
• Zero-Shot Deep Domain Adaptation
• Conditional Coupled Generative Adversarial Networks for Zero-Shot Domain Adaptation
• Adversarial Learning for Zero-shot Domain Adaptation
• A Grassmannian Approach to Zero-Shot Learning for Network Intrusion Detection