AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Frequency Switching Mechanism for Parameter-Efficient Multi-Task Learning

Shih-Wen Liu, Yen-Chang Chen, Wei-Ta Chu, Fu-En Yang, Yu-Chiang Frank Wang

CVPR 2026 · Architectures and efficiency › Pruning and efficient tuning · approach: Low-rank compression and merging

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 sine transformation to shared base (ablation)Free Sinewich · PASCAL-ContextDelta m (%): +3.67 -> +5.39Improved
add Gaussian low-pass filter (ablation)Free Sinewich · PASCAL-ContextDelta m (%): +4.82 -> +5.39Improved
add Lightweight Clock Net (ablation)Free Sinewich · PASCAL-ContextDelta m (%): +5.12 -> +5.39Improved
share one base matrix across tasks instead of independent bases (ablation)Free Sinewich · PASCAL-ContextDelta m (%): +5.03 -> +5.39Improved
share decoder weights via frequency switching instead of independent decoders (ablation)Free Sinewich · PASCAL-ContextDelta m (%): +5.31 -> +5.39Improved
increase rank 16 to 64 (ablation)Free Sinewich · PASCAL-ContextDelta m (%): +3.47 -> +5.39Improved
swap decoder HRNet to ASPP (ablation)Free Sinewich · PASCAL-ContextDelta m (%): +5.80 -> +7.14Improved
swap decoder HRNet to SegFormer (ablation)Free Sinewich · PASCAL-ContextDelta m (%): +5.80 -> +5.86No clear effect
Gaussian low-pass sigma 1.0 to 0.5 (ablation)Free Sinewich · PASCAL-ContextDelta m (%): +5.39 -> +4.90Hurt
Gaussian kernel size 7 to 5 or 9 (ablation)Free Sinewich · PASCAL-ContextDelta m (%): +5.39 -> +5.32No clear effect
use ImageNet-22K instead of ImageNet-1K pretraining (ablation)Free Sinewich · PASCAL-ContextDelta mImproved
Free Sinewich r=64 on NYUDv2 vs single-taskFree Sinewich · NYUDv2Delta m (%): -0.52Hurt

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