Unified Probabilistic Deep Continual Learning through Generative Replay and Open Set Recognition

05/28/2019
by   Martin Mundt, et al.
0

We introduce a unified probabilistic approach for deep continual learning based on variational Bayesian inference with open set recognition. Our model combines a probabilistic encoder with a generative model and a generative linear classifier that get shared across tasks. The open set recognition bounds the approximate posterior by fitting regions of high density on the basis of correctly classified data points and balances open-space risk with recognition errors. Catastrophic inference for both generative models is significantly alleviated through generative replay, where the open set recognition is used to sample from high density areas of the class specific posterior and reject statistical outliers. Our approach naturally allows for forward and backward transfer while maintaining past knowledge without the necessity of storing old data, regularization or inferring task labels. We demonstrate compelling results in the challenging scenario of incrementally expanding the single-head classifier for both class incremental visual and audio classification tasks, as well as incremental learning of datasets across modalities.

READ FULL TEXT

page 11

page 12

page 13

page 14

page 15

page 16

research
04/12/2022

Generative Negative Replay for Continual Learning

Learning continually is a key aspect of intelligence and a necessary abi...
research
01/04/2023

On Sequential Bayesian Inference for Continual Learning

Sequential Bayesian inference can be used for continual learning to prev...
research
06/03/2019

Continual Learning of New Sound Classes using Generative Replay

Continual learning consists in incrementally training a model on a seque...
research
04/19/2021

Continual Learning with Fully Probabilistic Models

We present an approach for continual learning (CL) that is based on full...
research
05/12/2023

RepCL: Exploring Effective Representation for Continual Text Classification

Continual learning (CL) aims to constantly learn new knowledge over time...
research
02/25/2019

S-TRIGGER: Continual State Representation Learning via Self-Triggered Generative Replay

We consider the problem of building a state representation model for con...
research
12/17/2020

Incremental Learning from Low-labelled Stream Data in Open-Set Video Face Recognition

Deep Learning approaches have brought solutions, with impressive perform...

Please sign up or login with your details

Forgot password? Click here to reset