Online Continual Learning in Image Classification: An Empirical Survey

by   Zheda Mai, et al.

Online continual learning for image classification studies the problem of learning to classify images from an online stream of data and tasks, where tasks may include new classes (class incremental) or data nonstationarity (domain incremental). One of the key challenges of continual learning is to avoid catastrophic forgetting (CF), i.e., forgetting old tasks in the presence of more recent tasks. Over the past few years, many methods and tricks have been introduced to address this problem, but many have not been fairly and systematically compared under a variety of realistic and practical settings. To better understand the relative advantages of various approaches and the settings where they work best, this survey aims to (1) compare state-of-the-art methods such as MIR, iCARL, and GDumb and determine which works best at different experimental settings; (2) determine if the best class incremental methods are also competitive in domain incremental setting; (3) evaluate the performance of 7 simple but effective trick such as "review" trick and nearest class mean (NCM) classifier to assess their relative impact. Regarding (1), we observe earlier proposed iCaRL remains competitive when the memory buffer is small; GDumb outperforms many recently proposed methods in medium-size datasets and MIR performs the best in larger-scale datasets. For (2), we note that GDumb performs quite poorly while MIR – already competitive for (1) – is also strongly competitive in this very different but important setting. Overall, this allows us to conclude that MIR is overall a strong and versatile method across a wide variety of settings. For (3), we find that all 7 tricks are beneficial, and when augmented with the "review" trick and NCM classifier, MIR produces performance levels that bring online continual learning much closer to its ultimate goal of matching offline training.


Supervised Contrastive Replay: Revisiting the Nearest Class Mean Classifier in Online Class-Incremental Continual Learning

Online class-incremental continual learning (CL) studies the problem of ...

Online Continual Learning Via Candidates Voting

Continual learning in online scenario aims to learn a sequence of new ta...

Tackling Online One-Class Incremental Learning by Removing Negative Contrasts

Recent work studies the supervised online continual learning setting whe...

PromptFusion: Decoupling Stability and Plasticity for Continual Learning

Continual learning refers to the capability of continuously learning fro...

Closed-Loop GAN for continual Learning

Sequential learning of tasks using gradient descent leads to an unremitt...

GRASP: A Rehearsal Policy for Efficient Online Continual Learning

Continual learning (CL) in deep neural networks (DNNs) involves incremen...

BeGin: Extensive Benchmark Scenarios and An Easy-to-use Framework for Graph Continual Learning

Continual Learning (CL) is the process of learning ceaselessly a sequenc...

Please sign up or login with your details

Forgot password? Click here to reset