Model Selection for Generalized Zero-shot Learning

11/08/2018
by   Hongguang Zhang, et al.
0

In the problem of generalized zero-shot learning, the datapoints from unknown classes are not available during training. The main challenge for generalized zero-shot learning is the unbalanced data distribution which makes it hard for the classifier to distinguish if a given testing sample comes from a seen or unseen class. However, using Generative Adversarial Network (GAN) to generate auxiliary datapoints by the semantic embeddings of unseen classes alleviates the above problem. Current approaches combine the auxiliary datapoints and original training data to train the generalized zero-shot learning model and obtain state-of-the-art results. Inspired by such models, we propose to feed the generated data via a model selection mechanism. Specifically, we leverage two sources of datapoints (observed and auxiliary) to train some classifier to recognize which test datapoints come from seen and which from unseen classes. This way, generalized zero-shot learning can be divided into two disjoint classification tasks, thus reducing the negative influence of the unbalanced data distribution. Our evaluations on four publicly available datasets for generalized zero-shot learning show that our model obtains state-of-the-art results.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/04/2017

Feature Generating Networks for Zero-Shot Learning

Suffering from the extreme training data imbalance between seen and unse...
research
12/11/2017

Generalized Zero-Shot Learning via Synthesized Examples

We present a generative framework for generalized zero-shot learning whe...
research
04/01/2020

Generalized Zero-Shot Learning Via Over-Complete Distribution

A well trained and generalized deep neural network (DNN) should be robus...
research
12/16/2018

Classifier and Exemplar Synthesis for Zero-Shot Learning

Zero-shot learning (ZSL) enables solving a task without the need to see ...
research
10/11/2022

Efficient Gaussian Process Model on Class-Imbalanced Datasets for Generalized Zero-Shot Learning

Zero-Shot Learning (ZSL) models aim to classify object classes that are ...
research
04/06/2023

Synthetic Sample Selection for Generalized Zero-Shot Learning

Generalized Zero-Shot Learning (GZSL) has emerged as a pivotal research ...
research
10/20/2019

An Optimal Transport Framework for Zero-Shot Learning

We present an optimal transport (OT) framework for generalized zero-shot...

Please sign up or login with your details

Forgot password? Click here to reset