AI Paper Atlas

Research map / Continual learning / Class-incremental

Quantum-Gated Task-interaction Knowledge Distillation for Pre-trained Model-based Class-Incremental Learning

Linjie Li, Huiyu Xiao, Jiarui Cao, Zhenyu Wu, Yang Ji

CVPR 2026 · Continual learning › Class-incremental · approach: Exemplar-efficient class-incremental learning · 0 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 quantum gating module (QGTM) (ablation)adapter-based PTM CIL baseline · CIFAR100 B0-Inc20average incremental accuracy: 78.42 -> 88.59Improved
add quantum gating module (QGTM) (ablation)adapter-based PTM CIL baseline · CUB200 B0-Inc20average incremental accuracy: 65.26 -> 91.73Improved
add quantum gating module (QGTM) (ablation)adapter-based PTM CIL baseline · ImageNet-A B0-Inc10final accuracy: 37.89 -> 51.79Improved
add task-interaction distillation loss L_QKD (ablation)QKD with QGTM · CIFAR100 B0-Inc20average incremental accuracy: 88.59 -> 92.69Improved
add task-interaction distillation loss L_QKD (ablation)QKD with QGTM · ImageNet-A B0-Inc10final accuracy: 51.79 -> 54.98Improved
add sparsity regularization L_s (ablation)QKD with QGTM and L_QKD · CIFAR100 B0-Inc20average incremental accuracy: 92.69 -> 93.76Improved
add sparsity regularization L_s (ablation)QKD with QGTM and L_QKD · CUB200 B0-Inc20final accuracy: 89.42 -> 90.20Improved
use quantum gate instead of MLP task recognizer (ablation)QKD · ImageNet-R B0-Inc20average accuracy: 80.25 -> 81.79Improved
use quantum gate instead of cosine similarity recognizer (ablation)QKD · ImageNet-R B0-Inc20average accuracy: 80.32 -> 81.79Improved
use quantum gate instead of attention recognizer (ablation)QKD · CUB200 B0-Inc20average accuracy: 92.57 -> 93.54Improved
feed first-task adapter A1 features to the gate (ablation)QKD · CIFAR100 B0-Inc10final accuracy: 88.83 -> 90.20Improved
use two adapters [A1,A2] instead of A1 as gate input (ablation)QKD · CIFAR100 B0-Inc10final accuracy: 90.20 -> 89.74Hurt

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