AI Paper Atlas

Research map / Detection and segmentation / CNN features

Superpixel Convolutional Networks Using Bilateral Inceptions

Raghudeep Gadde, Varun Jampani, Martin Kiefel, Daniel Kappler, Peter V. Gehler

ECCV 2016 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 130 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 BI(6,2) module, training only the moduleDeepLab · Pascal VOC12 testIoU: 68.9 -> 70.8Improved
also train FC layers jointly with BI(6,2) (ablation)DeepLab + BI(6,2) · Pascal VOC12 testIoU: 70.8 -> 71.5Improved
use more kernels in the BI module (2 to 6 kernels at fc6) (ablation)DeepLab + BI · Pascal VOC12 testIoU: 71.5 -> 72.9Improved
stack two BI modules (6,2 and 7,6) instead of one (ablation)DeepLab + BI · Pascal VOC12 testIoU: 71.5 -> 73.6Improved
use 10 kernels at fc8 (BI(8,10)) instead of 6 kernels at fc7 (ablation)DeepLab + BI · Pascal VOC12 testIoU: 73.1 -> 72.0Hurt
finetune the entire network (FULL) rather than BI+FC only (ablation)DeepLab + BI(6,2)-BI(7,6) · Pascal VOC12 testIoU: 73.6 -> 74.1Improved
add DenseCRF on top of the full BI model (ablation)DeepLab + BI(6,2)-BI(7,6) · Pascal VOC12 testIoU: 74.1 -> 75.1Improved
replace DenseCRF post-processing with BI(6,2)-BI(7,6) modulesDeepLab · Pascal VOC12 testIoU: 72.7 -> 73.6Improved
replace deconvolution and DenseCRF with BI modulesDeconvNet / CRFasRNN · Pascal VOC12 testIoU: 74.7 -> 74.9Improved
insert BI modules after fc7 and fc8 of AlexNetAlexNet · MINC testclass accuracy: 55.3 -> 69.4Improved
replace DenseCRF with BI modulesAlexNet · MINC testtotal accuracy: 71.0 -> 72.8Improved
insert BI(6,2)-BI(7,6) modulesDeepLab · Cityscapes val (full-res.)IoU: 65.7 -> 66.9Improved

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