AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Towards Accurate Binary Neural Networks via Modeling Contextual Dependencies

Xingrun Xing, Yangguang Li, Wei Li, Wenrui Ding, Yalong Jiang, Yufeng Wang, Jing Shao, Chunlei Liu, Xianglong Liu

ECCV 2022 · Architectures and efficiency › CNN design · approach: Efficient CNN scaling and dynamic inference · 9 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 binary MLP blocks replacing last conv blocksReActNet-A · ImageNet-1K valtop-1 accuracy: 69.4 -> 71.8Improved
add contextual dynamic embeddings to binary convolutions (ablation)BCDNet-A · ImageNet-1K valtop-1 accuracy: 71.8 -> 72.3Improved
add binary MLP blocks to ResNet-18 ReActNet (ablation)ReActNet (R18) · ImageNet-1K val (ResNet-18)top-1 accuracy: 65.5 -> 66.9Improved
add dynamic embeddings on R18 (ablation)BCDNet-A (R18) · ImageNet-1K val (ResNet-18)top-1 accuracy: 66.9 -> 67.9Improved
use BCDNet-A instead of ReActNet-A, from scratchReActNet-A · Fine-grained averageaccuracy: 23.2 -> 24.7Improved
add ImageNet pretraining and binary MLPs (ablation)ReActNet-A · Fine-grained average (pretrained)accuracy: 78.9 -> 84.2Improved
BCDNet-A vs ReActNet-A on Flowers and Aircraft from scratchReActNet-A · Flowers, Aircraft (from scratch)accuracy: 29.8 -> 25.0Hurt
replace conv blocks with MLPs only in last stage (ablation)ReActNet-18 · ImageNet-1K valtop-1 accuracy: 61.89 -> 63.58Improved
replace convs in all four stages instead of last only (ablation)BCDNet-18 · ImageNet-1K valtop-1 accuracy: 63.58 -> 63.10Hurt
use 1 BiMLP instead of conv in last stage (ablation)ReActNet-18 · ImageNet-1K valtop-1 accuracy: 61.89 -> 61.32Hurt
use 3 BiMLPs instead of 1 (ablation)BCDNet-18 · ImageNet-1K valtop-1 accuracy: 61.32 -> 63.58Improved
add short-range branch (P-S-L vs P-L-L) (ablation)BCDNet · ImageNet-1K val 600Ktop-1 accuracy: 70.79 -> 71.76Improved

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