AI Paper Atlas

Research map / Detection and segmentation / CNN features

Learnable Histogram: Statistical Context Features for Deep Neural Networks

Zhe Wang, Hongsheng Li, Wanli Ouyang, Xiaogang Wang

ECCV 2016 · Detection and segmentation › CNN features · approach: Local features and context in CNNs · 58 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 the learnable histogram layer (HistNet-SS) to FCNVGG-FCN · SIFTFlowper-pixel accuracy: 0.860 -> 0.879Improved
add the learnable histogram layer (HistNet-SS) to FCNVGG-FCN · Stanford backgroundper-pixel accuracy: 0.851 -> 0.871Improved
add the learnable histogram layer (HistNet-OD) to faster-RCNNfaster RCNN · VOC 2007 testmAP: 69.5 -> 71.4Improved
add the learnable histogram layer to DeepLabDeepLab · VOC 2012 segmentationmean IOU: 64.2 -> 67.5Improved
learn bin centers and widths instead of fixing them (ablation)HistNet-SS · SIFTFlowper-pixel accuracy: 0.872 -> 0.879Improved
lock histogram kernels to keep physical meaning instead of unlocking all (ablation)HistNet-SS · SIFTFlowper-pixel accuracy: 0.870 -> 0.879Improved
use histogram (statistical) context instead of global-pooled fc7 features (ablation)HistNet-SS · SIFTFlowper-pixel accuracy: 0.870 -> 0.879Improved
use histogram context instead of global-pooled score features (ablation)HistNet-SS · SIFTFlowper-pixel accuracy: 0.873 -> 0.879Improved
use histogram context instead of fc7 global features (ablation)HistNet-OD · VOC 2007 testmAP: 0.704 -> 0.714Improved
learn histogram parameters instead of fixing them (ablation)HistNet-OD · VOC 2007 testmAP: 0.707 -> 0.714Improved
add a second recurrent histogram layer (R-HistNet-SS) (ablation)HistNet-SS · SIFTFlowper-pixel accuracy: 0.879 -> 0.880No clear effect
add fully connected CRF post-processingHistNet-SS · SIFTFlowper-class accuracy: 0.5 -> 0.512Improved

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