AI Paper Atlas

Research map / Continual learning / Class-incremental

Multi-Centroid Task Descriptor for Dynamic Class Incremental Inference

Tenghao Cai, Zhizhong Zhang, Xin Tan, Yanyun Qu, Guannan Jiang, Chengjie Wang, Yuan Xie

CVPR 2023 · Continual learning › Class-incremental · approach: Exemplar-efficient class-incremental learning · 7 citations (OpenAlex)

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 the multi-centroid dynamic inference gate to DERDER · CIFAR100-B0, 5/10/20/50 stepsaverage accuracy (%): 76.80±0.79 -> 78.15±0.58; 75.36±0.36 -> 77.40±0.94; 74.09±0.33 -> 76.20±1.18; 72.41±0.36 -> 75.81±1.38Improved
Add the multi-centroid dynamic inference gate to DERDER · CIFAR100-B50, 2/5/10 stepsaverage accuracy (%): 74.61±0.52 -> 76.72±0.62; 73.21±0.78 -> 76.19±0.29; 72.81±0.88 -> 75.43±0.38Improved
Add the multi-centroid dynamic inference gate to DERDER · ImageNet100-B0S10top-1 average accuracy (%): 77.18 -> 80.46Improved
Add the multi-centroid dynamic inference gate to DERDER · ImageNet1000-B0S10top-1 average accuracy (%): 68.84 -> 70.80Improved
Add the multi-centroid dynamic inference gate to DERDER · ImageNet100-B50S10top-1 average accuracy (%): 78.20 -> 79.83Improved
Add RandAugment to the dynamic inference network training (ablation)Dynamic inference gate · CIFAR100-B0S10average accuracy (%): 75.38 -> 75.64Improved
Add knowledge distillation with data augmentation (ablation)Dynamic inference gate · CIFAR100-B0S10average accuracy (%): 75.64 -> 76.19Improved
Add logit adjustment to the gate and data augmentation (ablation)Dynamic inference gate · CIFAR100-B0S10average accuracy (%): 75.64 -> 76.45Improved
Add data augmentation, knowledge distillation, and logit adjustment (ablation)Dynamic inference gate · CIFAR100-B0S10average accuracy (%): 75.38 -> 77.40Improved
Add supernet knowledge distillation (ablation)DER · CIFAR100-B0S10average accuracy (%): 76.88 -> 76.75Hurt
Use the multi-centroid descriptor instead of CCCG's task classifier (ablation)Task-ID inference on CIFAR100-B0S10 · CIFAR100-B0S10average accuracy (%): 68.52 -> 77.40Improved
Use the multi-centroid descriptor instead of CCCG's task classifier (ablation)Task-ID inference on CIFAR100-B50S10 · CIFAR100-B50S10average accuracy (%): 55.62 -> 75.17Improved

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