AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Towards Disentangling Information Paths with Coded ResNeXt

Apostolos Avranas, Marios Kountouris

NeurIPS 2022 · Architectures and efficiency › RNNs and normalization · approach: Representation geometry and collapse · 1 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
force subNN specialization with coding (Coded ResNeXt vs ResNeXt)ResNeXt · CIFAR-10accuracy: 93.66% -> 94.41%Improved
same on CIFAR-100ResNeXt · CIFAR-100accuracy: 76.86% -> 78.76%Improved
same on ImageNetResNeXt-50 · ImageNetaccuracy: 79.50% -> 80.24%Improved
remove inactive subNNs from a block (ablation)Coded ResNeXt · CIFAR/ImageNet valaccuracyImproved
remove active subNNs from a block (ablation)Coded ResNeXt · CIFAR/ImageNet valaccuracyHurt
extract binary classifiers from ResNeXt instead of Coded ResNeXtResNeXt · CIFAR-10precision: 93% -> 13%Hurt
concatenate subNN outputs instead of summing (ablation)Coded ResNeXt · BC extractionprecision: precision < 20%Hurt
increase mu from 2 to 4 (ablation)Coded ResNeXt-50 · ImageNetaccuracy: 80.24% -> 79.81%Hurt
increase mu from 2 to 4 (ablation)Coded ResNeXt-50 · ImageNetearly decoder accuracy: 2.38% -> 4.6%Improved
use stage ratios (24/32,16/32,8/32) at s2-s4 instead of (16/32, 8/32) at s3,s4 (ablation)Coded ResNeXt-50 · ImageNet 150 epochsaccuracy: 78.1% -> worse than 77%Hurt
add early-decoder agreement to temperature scaling (h_aug vs h_T)Calibration · CIFAR-10MCE: 24.35% -> 24.14%Improved
add early-decoder agreement to temperature scalingCalibration · CIFAR-10ECE: 0.70% -> 0.70%No clear effect

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