AI Paper Atlas

Research map / Detection and segmentation / CNN features

Composite Binary Decomposition Networks

AAAI 2019 · Detection and segmentation › CNN features · approach: Efficient network training and design · 2 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
Transfer full-precision ResNet-18 to CBDNetResNet-18 · ImageNet valtop-1 accuracy (%): 66.41 -> 65.27Hurt
Transfer full-precision VGG-16 to CBDNetVGG-16 · ImageNet valtop-5 accuracy (%): 88.44 -> 87.81Hurt
Transfer full-precision DenseNet-121 to CBDNetDenseNet-121 · ImageNet valtop-1 accuracy (%): 74.41 -> 73.13Hurt
Use CBDNet instead of BWDResNet-152 · ImageNet valtop-5 accuracy (%): 90.25 -> 91.61Helped
Use CBDNet instead of BWDVGG-16 · ImageNet valtop-5 accuracy (%): 86.28 -> 87.81Helped
Transfer SSD300 to CBDNetSSD300 · VOC 2007 testmAP: 1.34%Hurt
Transfer SegNet to CBDNetSegNet · Cityscapes val, 11 classesmIOU: 0.8%Hurt
Use CBDNet instead of BWDSegNet · Cityscapes val, 11 classesmIOU: more than 2.75%Helped
Use CBDNet instead of BWDVGG-16 · VGG-16 conv layer, projected to networkspeedup: 2.07× -> 4.02×Helped

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