AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Truncating Wide Networks Using Binary Tree Architectures

Yan Zhang, Mete Ozay, Shuohao Li, Takayuki Okatani

ICCV 2017 · Architectures and efficiency › RNNs and normalization · approach: Theory of depth and width · 4 citations (OpenAlex)

Read the paper

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 Wide ResNet blocks with binary tree blocks (d=12,k=2,n=4)Wide ResNet · CIFAR-100classification error (%): 20.43 -> 19.06Improved
replace Wide ResNet blocks with binary tree blocks (d=12,k=4,n=2)Wide ResNet · CIFAR-100classification error (%): 20.43 -> 19.22Improved
replace Wide ResNet blocks with binary tree blocks (d=10,k=2,n=3)Wide ResNet · CIFAR-100classification error (%): 20.75 -> 19.29Improved
replace Wide ResNet blocks with binary tree blocks (d=10,k=2,n=2)Wide ResNet · CIFAR-100classification error (%): 21.59 -> 20.48Improved
replace Wide ResNet blocks with binary tree blocks (d=4,k=3,n=4)Wide ResNet · CIFAR-100classification error (%): 22.89 -> 22.19Improved
use a single BitBlock per group with k=4 (d=10,k=4,n=1)BitNet · CIFAR-100classification error (%): 21.59 -> 23.88Hurt
replace Wide ResNet blocks with binary tree blocks (d=4,k=6,n=2)Wide ResNet · CIFAR-100classification error (%): 22.89 -> 23.87Hurt
add binary tree block depth k from 1 to 2 (d=12,n=2) (ablation)BitNet · CIFAR-100classification error (%): 23.80 -> 19.86Improved
increase block depth k beyond 3 (d=12,n=2) (ablation)BitNet · CIFAR-100classification error (%): 18.97 -> 19.22No clear effect
add binary tree block depth k from 1 to 3 (d=4,n=4) (ablation)BitNet · CIFAR-100classification error (%): 23.54 -> 22.19Improved
add concatenation-based BitBlock (b(4,4,3)-38) versus plain network without shortcuts (ablation)plainnet-38 · CIFAR-100classification error (%): 29.13 -> 22.60Improved
increase number of blocks n and reduce k (b(4,2,6)-38 versus b(4,6,2)-38) (ablation)BitNet depth 38 · CIFAR-100first-layer gradient magnitudeHurt

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