AI Paper Atlas

Research map / Detection and segmentation / CNN features

Deep Feature Factorization For Concept Discovery

Edo Collins, Radhakrishna Achanta, Sabine Susstrunk

ECCV 2018 · Detection and segmentation › CNN features · approach: Local features and context in CNNs · 91 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 DFF (ablation)DFF · PASCAL VOC 2007 co-localizationCorLoc (%): 42.87 -> 43.51Improved
add CRF post-processing to DFF (ablation)DFF (k=1) · iCoseg Elephants object co-segmentationIoU (%): 65 -> 76Improved
add CRF post-processing to DFF (ablation)DFF (k=1) · iCoseg Taj Mahal object co-segmentationIoU (%): 41 -> 51Improved
add CRF post-processing to DFF (ablation)DFF (k=1) · iCoseg Pyramids object co-segmentationIoU (%): 57 -> 70Improved
add CRF post-processing to DFF (ablation)DFF (k=1) · iCoseg Gymnastics1 object co-segmentationIoU (%): 43 -> 52Improved
add CRF post-processing to DFF (ablation)DFF (k=1) · iCoseg Statue of Liberty object co-segmentationIoU (%): 49 -> 62Improved
add CRF post-processing to DFF (ablation)DFF (k=3) · PASCAL-Parts cow headavg IoU (%): 40.53 -> 45.20Improved
add CRF post-processing to DFF (ablation)DFF (k=3) · PASCAL-Parts horse headavg IoU (%): 28.85 -> 31.05Improved
add CRF post-processing to DFF (ablation)DFF (k=3) · PASCAL-Parts cow neck+torsoavg IoU (%): 59.48 -> 58.87Hurt
add CRF post-processing to DFF (ablation)DFF (k=3) · PASCAL-Parts horse neck+torsoavg IoU (%): 54.77 -> 53.18Hurt
use unsupervised DFF instead of best prior co-localization method (Le V)Le (V) · PASCAL VOC 2007 co-localizationCorLoc (%): 41.97 -> 42.87Improved
use ResNet-101 instead of VGG family (ablation)DFF · iCosegaverage IoUHurt

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