Adversarial Training of Variational Auto-encoders for Continual Zero-shot Learning

02/07/2021
by   Subhankar Ghosh, et al.
15

Most of the existing artificial neural networks(ANNs) fail to learn continually due to catastrophic forgetting, while humans can do the same by maintaining previous tasks' performances. Although storing all the previous data can alleviate the problem, it takes a large memory, infeasible in real-world utilization. We propose a continual zero-shot learning model that is more suitable in real-case scenarios to address the issue that can learn sequentially and distinguish classes the model has not seen during training. We present a hybrid network that consists of a shared VAE module to hold information of all tasks and task-specific private VAE modules for each task. The model's size grows with each task to prevent catastrophic forgetting of task-specific skills, and it includes a replay approach to preserve shared skills. We demonstrate our hybrid model is effective on several datasets, i.e., CUB, AWA1, AWA2, and aPY. We show our method is superior on class sequentially learning with ZSL(Zero-Shot Learning) and GZSL(Generalized Zero-Shot Learning).

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/26/2021

Dynamic VAEs with Generative Replay for Continual Zero-shot Learning

Continual zero-shot learning(CZSL) is a new domain to classify objects s...
research
01/22/2021

Generative Replay-based Continual Zero-Shot Learning

Zero-shot learning is a new paradigm to classify objects from classes th...
research
05/17/2021

Shared and Private VAEs with Generative Replay for Continual Learning

Continual learning tries to learn new tasks without forgetting previousl...
research
11/23/2022

Evolutionary Generalized Zero-Shot Learning

An open problem on the path to artificial intelligence is generalization...
research
03/19/2021

Online Lifelong Generalized Zero-Shot Learning

Methods proposed in the literature for zero-shot learning (ZSL) are typi...
research
11/27/2020

Direct Evolutionary Optimization of Variational Autoencoders With Binary Latents

Discrete latent variables are considered important for real world data, ...
research
11/17/2020

Generalized Continual Zero-Shot Learning

Recently, zero-shot learning (ZSL) emerged as an exciting topic and attr...

Please sign up or login with your details

Forgot password? Click here to reset