AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Kernelized Sparse Fine-Tuning With Bi-Level Parameter Competition for Vision Models

TPAMI 2026 · Architectures and efficiency › Pruning and efficient tuning · approach: Adapter-based parameter-efficient tuning

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
replace linear kernel with non-linear P-Linear kernel (ablation)Kernelized LoRA (no sparsification) · VTAB-1k ViT-B/16mean accuracy: 75.2% v.s. 74.2%Improved
add sparsification to a linear-kernel LoRA (ablation)Linear kernel LoRA · VTAB-1k ViT-B/16mean accuracy: 74.2% v.s. 65.7%Hurt
add sparsification to a P-Linear kernel LoRA (ablation)P-Linear kernelized LoRA · VTAB-1k ViT-B/16mean accuracy: 75.2% v.s. 76.9%Improved
use Mix-K instead of P-Linear kernel (with sparsification) (ablation)SNELLA · VTAB-1k ViT-B/16mean accuracy: 77.2% v.s. 76.9%Improved
use Mix-K instead of P-Linear kernel (no sparsification) (ablation)Kernelized LoRA · VTAB-1k ViT-B/16mean accuracy: 75.7% v.s. 75.2%Improved
normalize RBF kernel values (ablation)RBF kernelized LoRA · VTAB-1k ViT-B/16mean accuracy: 75.2% v.s. 58.7%Improved
use Mix-K instead of normalized RBF kernel (ablation)Kernelized LoRA · VTAB-1k ViT-B/16mean accuracy: 75.7% v.s. 75.2%Improved
add within-layer competition sparsity (ablation)Kernelized LoRA · VTAB-1k ViT-B/16mean accuracy: 75.7% v.s. 77.0%Improved
add across-layer competition (ablation)KLoRA with within-layer competition · VTAB-1k ViT-B/16mean accuracy: 77.0% v.s. 77.2%Improved
use sensitivity instead of magnitude as layer importance (alloc per epoch) (ablation)SNELLA · VTAB-1k ViT-B/16 (0.01% params)mean accuracy: 75.1 -> 75.3Improved
reallocate sparsity per epoch instead of per step (sensitivity) (ablation)SNELLA · VTAB-1k ViT-B/16 (0.01% params)mean accuracy: 75.0 -> 75.3Improved
add budget decay scheduling (linear) vs constant budget (ablation)SNELLA-32 · VTAB-1k 4 datasetsmean accuracy: 61.07% v.s. 63.50%Improved

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