AI Paper Atlas

Research map / Detection and segmentation / CNN features

Dynamic Filtering with Large Sampling Field for ConvNets

Jialin Wu, Dai Li, Yu Yang, Chandrajit Bajaj, Xiangyang Ji

ECCV 2018 · Detection and segmentation › CNN features · approach: Local features and context in CNNs · 50 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 an LS-DFN layerR-FCN · VOC 2007 detectionmAP: 77.6 -> 79.2Improved
add an LS-DFN layerCoupleNet · VOC 2007 detectionmAP: 80.4 -> 81.7Improved
sample 3x3 neighbour regions instead of only the identical position (s=1 to s=3) (ablation)LS-DFN, C'=24, with attention · VOC 2007 detectionmAP: 72.5 -> 78.6Improved
increase samples from s=3 to s=5 (ablation)LS-DFN, C'=24, with attention · VOC 2007 detectionmAP: 78.6 -> 78.6No clear effect
add attention mechanism (stride 1) (ablation)LS-DFN, C'=24 · VOC 2007 detectionmAP: 77.4 -> 78.1Improved
add attention mechanism (C'=32, stride 1) (ablation)LS-DFN · VOC 2007 detectionmAP: 77.6 -> 78.6Improved
add residual learning to kernel generation (ablation)LS-DFN, C'=24, with attention · VOC 2007 detectionmAP: 68.1 -> 78.68Improved
add residual learning without attention (ablation)LS-DFN, C'=24 · VOC 2007 detectionconvergence: fails to converge -> 77.4Improved
increase stride from 1 to 2 (C'=24, with attention) (ablation)LS-DFN · VOC 2007 detectionmAP: 78.1 -> 78.6Improved
increase stride from 1 to 2 (C'=32, with attention) (ablation)LS-DFN · VOC 2007 detectionmAP: 78.6 -> 78.0Hurt
add LS-DFN layer to DeepLabV2 + CRFDeepLabV2 · VOC 2012 segmentationmean IoU: 79.7 -> 81.1Improved
replace dilated convolutions by LS-DFN with stridesDeepLabV2 · VOC 2012 segmentationmean IoU: 79.7 -> 80.4Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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