A Generative Framework for Zero-Shot Learning with Adversarial Domain Adaptation

06/07/2019
by   Varun Khare, et al.
0

In this paper, we present a domain adaptation based generative framework for Zero-Shot Learning. We explicitly target the problem of domain shift between the seen and unseen class distribution in Zero-Shot Learning (ZSL) and seek to minimize it by developing a generative model and training it via adversarial domain adaptation. Our approach is based on end-to-end learning of the class distributions of seen classes and unseen classes. To enable the model to learn the class distributions of unseen classes, we parameterize these class distributions in terms of the class attribute information (which is available for both seen and unseen classes). This provides a very simple way to learn the class distribution of any unseen class, given only its class attribute information, and no labeled training data. Training this model with adversarial domain adaptation provides robustness against the distribution mismatch between the data from seen and unseen classes. Through a comprehensive set of experiments, we show that our model yields superior accuracies as compared to various state-of-the-art ZSL models, on a variety of benchmark datasets.

READ FULL TEXT
research
07/25/2017

A Simple Exponential Family Framework for Zero-Shot Learning

We present a simple generative framework for learning to predict previou...
research
02/01/2020

Domain segmentation and adjustment for generalized zero-shot learning

In the generalized zero-shot learning, synthesizing unseen data with gen...
research
07/15/2021

Context-Conditional Adaptation for Recognizing Unseen Classes in Unseen Domains

Recent progress towards designing models that can generalize to unseen d...
research
11/17/2022

Targeted Attention for Generalized- and Zero-Shot Learning

The Zero-Shot Learning (ZSL) task attempts to learn concepts without any...
research
03/02/2020

Addressing target shift in zero-shot learning using grouped adversarial learning

In this paper, we present a new paradigm to zero-shot learning (ZSL) tha...
research
09/12/2017

Joint Dictionaries for Zero-Shot Learning

A classic approach toward zero-shot learning (ZSL) is to map the input d...
research
03/01/2021

Counterfactual Zero-Shot and Open-Set Visual Recognition

We present a novel counterfactual framework for both Zero-Shot Learning ...

Please sign up or login with your details

Forgot password? Click here to reset