AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Broadcasting Convolutional Network for Visual Relational Reasoning

Simyung Chang, John Yang, SeongUk Park, Nojun Kwak

ECCV 2018 · Vision-language and multimodal › Human and embodied modeling · approach: Abstract visual reasoning benchmarks · 22 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
add BCN (global max-pool broadcast) to the baseline CNN3-layer CNN · Scaled-MNISTclassification accuracy: 84.4% -> 97.5%Improved
use max pooling instead of average pooling in BCN (ablation)Base + BCN · Scaled-MNISTclassification accuracy: 92.7% -> 97.5%Improved
add BCN on top of coordinates plus skip-connection (ablation)Base + CCE + Skip-connection · Scaled-MNISTlocalization error: 0.071 -> 0.023Improved
add coordinate channels (CCE) alone to baseline (ablation)3-layer CNN · Scaled-MNISTlocalization error: 0.151 -> 0.088Improved
add BCN to baseline CNN4-layer CNN · STL-10 (from scratch)accuracy: 68.75% -> 72.18%Improved
use BCN instead of a plain skip-connection of the same convolutions (ablation)4-layer CNN · STL-10 (from scratch)accuracy: 69.79% -> 72.18%Improved
add BCN to ResNet-18ResNet-18 · STL-10 (from scratch)accuracy: 76.27% -> 77.00%Improved
add BCN and coordinate encoding to multiRN (ablation)CNN+multiRN · Sort-of-CLEVRrelational accuracy: 88.7% -> 92.9%Improved
add coordinate embedding to a CNN+MLP model (ablation)CNN+MLP · Sort-of-CLEVRrelational accuracy: 74.2% -> 72.9%Hurt
use stride 1 in the last conv layer (CNN_h) for multiRNmultiRN · Sort-of-CLEVRrelational accuracy: 92.9% -> 96.7%Improved
replace RN with multiRNCNN+LSTM · CLEVR (pixels)overall accuracy: 90.9 -> 92.3Improved
use CNN_h with multiRN and enlarge input to 224x224CNN_h+LSTM+multiRN · CLEVR (pixels)overall accuracy: 97.2 -> 97.7Improved

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