Generalized Continual Zero-Shot Learning

11/17/2020
by   Chandan Gautam, et al.
3

Recently, zero-shot learning (ZSL) emerged as an exciting topic and attracted a lot of attention. ZSL aims to classify unseen classes by transferring the knowledge from seen classes to unseen classes based on the class description. Despite showing promising performance, ZSL approaches assume that the training samples from all seen classes are available during the training, which is practically not feasible. To address this issue, we propose a more generalized and practical setup for ZSL, i.e., continual ZSL (CZSL), where classes arrive sequentially in the form of a task and it actively learns from the changing environment by leveraging the past experience. Further, to enhance the reliability, we develop CZSL for a single head continual learning setting where task identity is revealed during the training process but not during the testing. To avoid catastrophic forgetting and intransigence, we use knowledge distillation and storing and replay the few samples from previous tasks using a small episodic memory. We develop baselines and evaluate generalized CZSL on five ZSL benchmark datasets for two different settings of continual learning: with and without class incremental. Moreover, CZSL is developed for two types of variational autoencoders, which generates two types of features for classification: (i) generated features at output space and (ii) generated discriminative features at the latent space. The experimental results clearly indicate the single head CZSL is more generalizable and suitable for practical applications.

READ FULL TEXT

page 1

page 2

page 3

page 4

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
03/19/2021

Online Lifelong Generalized Zero-Shot Learning

Methods proposed in the literature for zero-shot learning (ZSL) are typi...
research
06/24/2020

Insights from the Future for Continual Learning

Continual learning aims to learn tasks sequentially, with (often severe)...
research
02/23/2021

Meta-Learned Attribute Self-Gating for Continual Generalized Zero-Shot Learning

Zero-shot learning (ZSL) has been shown to be a promising approach to ge...
research
02/07/2021

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

Most of the existing artificial neural networks(ANNs) fail to learn cont...
research
03/30/2022

Unseen Classes at a Later Time? No Problem

Recent progress towards learning from limited supervision has encouraged...
research
08/11/2023

Complex Facial Expression Recognition Using Deep Knowledge Distillation of Basic Features

Complex emotion recognition is a cognitive task that has so far eluded t...

Please sign up or login with your details

Forgot password? Click here to reset