AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Deep Lookup Network

Yulan Guo, Longguang Wang, Wendong Mao, Xiaoyu Dong, Yingqian Wang, Li Liu, Wei An

TPAMI 2025 · Architectures and efficiency › CNN design · approach: Efficient CNN scaling and dynamic inference · 4 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
make lookup tables learnable instead of fixed (ablation)LookupNet · CIFAR-10/CIFAR-100 (ResNet-20)top-1 accuracy: 91.80/67.77 -> 92.68/68.96Improved
construct tables with cumulative softmax distributions instead of independent random-init values (ablation)LookupNet · CIFAR-10 (ResNet-20)top-1 accuracy: 19.17 -> 92.68Improved
construct tables with cumulative softmax instead of independent step-initialized values (ablation)LookupNet · CIFAR-10 (ResNet-20)top-1 accuracy: 43.52 -> 92.68Improved
increase table granularity from 17 to 33 (ablation)LookupNet · CIFAR-10/CIFAR-100 (ResNet-20)top-1 accuracy: 92.21/67.85 -> 92.68/68.96Improved
increase table granularity from 33 to 65 (ablation)LookupNet · CIFAR-10/CIFAR-100 (ResNet-20)top-1 accuracy: 92.68/68.96 vs. 92.70/68.97No clear effect
use exponential formulation of scale parameters (ablation)LookupNet · CIFAR-10/CIFAR-100 (ResNet-20)top-1 accuracy: 92.35/68.12 -> 92.47/68.51Improved
add gradient re-scaling across table cells (ablation)LookupNet · CIFAR-10/CIFAR-100 (ResNet-20)top-1 accuracy: 92.47/68.51 -> 92.68/68.96Improved
replace convolutions with lookup layersResNet-20 · CIFAR-10/CIFAR-100top-1 accuracy: 92.25 -> 92.68; 68.14 -> 68.97Improved
use lookup operation instead of addition-based AdderNetResNet-20 · CIFAR-10/CIFAR-100top-1 accuracy: 91.84/67.60 -> 92.68/68.97Improved
add 4-bit quantization to LookupNetResNet-20 · CIFAR-10 and Cortex-A15 energyaccuracy / energy: 92.68 -> 92.51; 75.0 -> 34.5 mJMixed
add pruning to LookupNetResNet-20 · CIFAR-10 and Cortex-A15 energyaccuracy / energy: 92.68 -> 92.55; 75.0 -> 36.0 mJMixed
replace convolutions with lookup layersVGG-Small · CIFAR-100top-1 accuracy: 72.73 -> 75.75Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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