AI Paper Atlas

Research map / Detection and segmentation / CNN features

Recurrent Instance Segmentation

Bernardino Romera-Paredes, Philip Hilaire Sean Torr

ECCV 2016 · Detection and segmentation › CNN features · approach: Boundary-aware instance segmentation · 332 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 CRF post-processing to RIS (ablation)RIS · PASCAL VOC 2012 val (multiple person segmentation)AP^r at 0.5 IoU: 46.7 -> 50.1Improved
add CRF post-processing to RIS (ablation)RIS · PASCAL VOC 2012 val (multiple person segmentation)AP^r averaged over IoU 0.1-0.9: 41.9 -> 43.7Improved
add CRF post-processing to RIS (ablation)RIS · CVPPP A1 leaf segmentationSymmetric Best Dice (%): 56.8 -> 66.6Improved
add CRF post-processing to RIS (ablation)RIS · CVPPP A1 leaf counting|DiC|: 1.1 -> 1.1No clear effect
add sum of predicted masks as extra input to the recurrent unit (ablation)RIS · multiple person segmentationAP^rNo clear effect
replace IoU-based loss with log-likelihood loss (ablation)RIS · multiple person segmentationAP^rHurt

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