AI Paper Atlas

Research map / Continual learning / Online and replay-based

Task-Aware Prompt Gradient Projection for Parameter-Efficient Tuning Federated Class-Incremental Learning

Hualong Ke, Jiangming Shi, Yachao Zhang, Fangyong Wang, Yuan Xie, Yanyun Qu

ICCV 2025 · Continual learning › Online and replay-based · approach: Unified and unsupervised continual frameworks · 2 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 TAPGP gradient projection (ablation)LANDER+VPT-Deep · CIFAR-100 (NIID(0.5), T=5)average accuracy: 64.58 -> 69.11Improved
add inter-task prompt replay (ablation)LANDER+VPT-Deep · CIFAR-100 (NIID(0.5), T=5)average accuracy: 64.58 -> 67.72Improved
add intra-task prompt replay (ablation)LANDER+VPT-Deep · CIFAR-100 (NIID(0.5), T=5)average accuracy: 64.58 -> 66.95Improved
add both intra- and inter-task replay (DLPR) (ablation)LANDER+VPT-Deep · CIFAR-100 (NIID(0.5), T=5)average accuracy: 64.58 -> 70.45Improved
add DLPR on top of TAPGP (ablation)TPPR · CIFAR-100 (NIID(0.5), T=5)average accuracy: 69.11 -> 73.84Improved
add TAPGP on top of DLPR (ablation)TPPR · CIFAR-100 (NIID(0.5), T=5)average accuracy: 70.45 -> 73.84Improved
add inter-task replay to TAPGP+intra (ablation)TPPR · CIFAR-100 (NIID(0.5), T=5)forgetting F: 16.83 -> 11.30Improved
replace LANDER with VPT-Deep prompt tuning backbone (ablation)LANDER · CIFAR-100 (NIID(0.5), T=5)average accuracy: 48.23 -> 64.58Improved
add VPT-Deep to LANDER (ablation)LANDER · CIFAR-100 (IID, T=5)forgetting F: 18.03 -> 27.74Hurt
add TPPR modules to LANDER+VPT-Deep (ablation)LANDER+VPT-Deep · Tiny-ImageNet (IID, T=10)average accuracy: 42.74 -> 65.96Improved
start gradient projection at deeper layer (us=6 vs us=0) (ablation)TAPGP · CIFAR-100 (NIID(0.5), T=5)average accuracyMixed
mixing prompts instead of calculating attention for inter-task replay (ablation)DLPR · CIFAR-100 (NIID(0.5))average accuracyImproved

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