A baseline on continual learning methods for video action recognition

04/20/2023
by   Giulia Castagnolo, et al.
0

Continual learning has recently attracted attention from the research community, as it aims to solve long-standing limitations of classic supervisedly-trained models. However, most research on this subject has tackled continual learning in simple image classification scenarios. In this paper, we present a benchmark of state-of-the-art continual learning methods on video action recognition. Besides the increased complexity due to the temporal dimension, the video setting imposes stronger requirements on computing resources for top-performing rehearsal methods. To counteract the increased memory requirements, we present two method-agnostic variants for rehearsal methods, exploiting measures of either model confidence or data information to select memorable samples. Our experiments show that, as expected from the literature, rehearsal methods outperform other approaches; moreover, the proposed memory-efficient variants are shown to be effective at retaining a certain level of performance with a smaller buffer size.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/09/2023

CLVOS23: A Long Video Object Segmentation Dataset for Continual Learning

Continual learning in real-world scenarios is a major challenge. A gener...
research
11/23/2022

Integral Continual Learning Along the Tangent Vector Field of Tasks

We propose a continual learning method which incorporates information fr...
research
09/11/2022

Continual Learning for Pose-Agnostic Object Recognition in 3D Point Clouds

Continual Learning aims to learn multiple incoming new tasks continually...
research
06/03/2019

Continual learning improves Internet video streaming

We describe Fugu, a continual learning algorithm for bitrate selection i...
research
06/12/2020

CPR: Classifier-Projection Regularization for Continual Learning

We propose a general, yet simple patch that can be applied to existing r...
research
11/27/2022

Neural Architecture for Online Ensemble Continual Learning

Continual learning with an increasing number of classes is a challenging...
research
07/11/2023

Domain-Agnostic Neural Architecture for Class Incremental Continual Learning in Document Processing Platform

Production deployments in complex systems require ML architectures to be...

Please sign up or login with your details

Forgot password? Click here to reset