AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

CaRe: Critical Parameter Rectification for Efficient Visual Modeling

Mingjia Li, Hongkun Xiong, Yuheng Shi, Hengxing Liu, Xiaojie Guo

ECCV 2026 · Architectures and efficiency › Pruning and efficient tuning · approach: Joint pruning and quantization · 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
use Softplus instead of identity as gate activation (ablation)CaReNet-M1 · ImageNet-1Ktop-1 accuracy (%): 72.9 -> 73.6Improved
use GELU instead of identity as gate activation (ablation)CaReNet-M1 · ImageNet-1Ktop-1 accuracy (%): 72.9 -> 73.5Improved
add a dense base weight to the gated term (ablation)CaRe (W = P1 ⊙ φ(P2)) · ImageNet-1Ktop-1 accuracy (%): 69.5 -> 73.6Improved
gate the single weight with no base weight (vs standard conv) (ablation)standard convolution · ImageNet-1Ktop-1 accuracy (%): 72.7 -> 69.5Hurt
keep the gated auxiliary term at inference (vs discarding after training) (ablation)CaReNet-M1 · ImageNet-1Ktop-1 accuracy (%): 60.1 -> 73.6Improved
use learned gated correction instead of RepVGG-style fixed correction (ablation)CaReNet-M1 · ImageNet-1Ktop-1 accuracy (%): 73.2 -> 73.6Improved
use two gated terms instead of one gated plus one dense term (ablation)CaReNet-M1 · ImageNet-1Ktop-1 accuracy (%): 73.6 -> 70.1Hurt
use Progressive fusion instead of final-stage-only fusion (ablation)CaReNet-M1 · ImageNet-1Ktop-1 accuracy (%): 73.1 -> 73.6Improved
use Progressive fusion instead of uniform-average fusion (ablation)CaReNet-M1 · ImageNet-1Ktop-1 accuracy (%): 72.9 -> 73.6Improved
add CaRe to ResNet-18ResNet-18 · ImageNet-1K (DeiT recipe)top-1 accuracy (%): 69.1 -> 69.3Improved
add CaRe to ViT-TinyViT-Tiny · ImageNet-1K (DeiT recipe)top-1 accuracy (%): 72.2 -> 72.4Improved
add CaRe to PoolFormerV2-S12PoolFormerV2-S12 · ImageNet-1K (DeiT recipe)top-1 accuracy (%): 77.7 -> 78.1Improved

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