AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Optimising for Interpretability: Convolutional Dynamic Alignment Networks

Moritz Böhle, Mario Fritz, Bernt Schiele

TPAMI 2022 · Architectures and efficiency › CNN design · approach: Compact CNN architectures

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
increase temperature T from 10 to 1000 (ablation)S-CoDA-SQ · CIFAR-10accuracy: 93.6% -> 93.2%Hurt
increase temperature (alignment pressure) (ablation)S-CoDA-SQ · CIFAR-10interpretability (localisation)Improved
use eDAU weight-bounded (WB) non-linearity instead of SQ/L2 with shared B (ablation)S-CoDA · CIFAR-10accuracy: 93.2% -> 94.0%Improved
add learnt patch embedding E(x) as input (ablation)S-eCoDA-WB · CIFAR-10accuracy: 94.0% -> 94.1%Improved
use WB rescaling instead of SQL-CoDA · ImagenetGPU memory: 30.0GB -> 9.7GBImproved
use WB rescaling instead of SQL-CoDA · Imagenettraining time: 14.1 minutes -> 8.7 minutesImproved
add data augmentationXL-CoDA-SQ · TinyImagenetaccuracy: 54.4% -> 58.4%Improved
replace last 4 ResNet-56 segments by CoDA layers (R1-C4) (ablation)ResNet-56 · CIFAR-10accuracy: 93.4% -> 93.8%No clear effect
replace last 5 ResNet-50 blocks by CoDA layers (R0-C5) (ablation)ResNet-50 · Imagenetaccuracy: 76.1% -> 71.4%Hurt
replace more ResNet segments by CoDA layers (ablation)ResNet hybrids · CIFAR-10 and Imagenetinterpretable depth (localisation)Improved
use CoDA layers rather than piece-wise linear ResNet blocks in the head (ablation)hybrid networks · CIFAR-10localisationImproved

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