AI Paper Atlas

Research map / Continual learning / Online and replay-based

Online Continual Learning with Contrastive Vision Transformer

Zhen Wang, Liu Liu, Yajing Kong, Jiaxian Guo, Dacheng Tao

ECCV 2022 · Continual learning › Online and replay-based · approach: Unified and unsupervised continual frameworks

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add focal contrastive loss (vs removing it) (ablation)CVT · CIFAR100 Task-free, buffer 500accuracy (%): 19.92 -> 24.45Improved
add focal contrastive loss (vs removing it) (ablation)CVT · CIFAR100 Task-free, buffer 500forgetting (%): 26.16 -> 21.86Improved
replace supervised contrastive loss with focal contrastive loss (ablation)CVT · CIFAR100 Task-free, buffer 500accuracy (%): 20.73 -> 24.45Improved
replace focal contrastive loss with supervised contrastive loss (no forgetting gain over no contrastive loss) (ablation)CVT · CIFAR100 Task-free, buffer 500forgetting (%): 26.16 -> 25.52No clear effect
add dual-classifier (vs removing it) (ablation)CVT · CIFAR100 Task-free, buffer 500accuracy (%): 22.08 -> 24.45Improved
add dual-classifier (vs removing it) (ablation)CVT · CIFAR100 Task-free, buffer 500forgetting (%): 29.81 -> 21.86Improved
add focal contrastive loss to ResNet18 (ablation)ResNet18 · CIFAR100 Task-free, buffer 500accuracy (%): 15.72 -> 17.49Improved
add dual-classifier to ResNet18 (ablation)ResNet18 · CIFAR100 Task-free, buffer 500accuracy (%): 15.72 -> 18.84Improved
replace ResNet18 with CVT architecture (minus L_FC) (ablation)online CL · CIFAR100 Task-free, buffer 500accuracy (%): 15.72 -> 19.92Improved
add focal contrastive loss (vs removing it) (ablation)CVT · TinyImageNet Task-free, buffer 500accuracy (%): 12.47 -> 14.71Improved
add dual-classifier (vs removing it) (ablation)CVT · TinyImageNet Task-free, buffer 500accuracy (%): 13.63 -> 14.71Improved
replace focal contrastive loss with supervised contrastive loss (ablation)CVT · TinyImageNet Task-free, buffer 500accuracy (%): 12.47 -> 12.59No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy