AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

On the Importance of Visual Context for Data Augmentation in Scene Understanding

Nikita Dvornik, Julien Mairal, Cordelia Schmid

TPAMI 2019 · Detection and segmentation › Open-set and few-shot detection · approach: Object-level representation learning · 92 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
paste objects at random locations instead of no copy-paste (ablation)Base-DA · VOC07-test single-categoryaverage AP (%): 58.0 -> 56.9Hurt
add context-driven placement over random placement (ablation)copy-paste DA · VOC07-test single-categoryaverage AP (%): 56.9 -> 64.0Improved
add context-driven placement to standard augmentation (ablation)Base-DA · VOC07-test single-categoryaverage AP (%): 58.0 -> 64.0Improved
add context-driven augmentation, multi-category (ablation)BlitzNet300 · VOC07-test multi-categorymAP (%): 64.6 -> 66.5Improved
add context-driven augmentation, multi-category (ablation)Faster R-CNN · VOC07-test multi-categorymAP (%): 63.1 -> 64.5Improved
add context-driven augmentation for segmentation (ablation)BlitzNet300 · VOC12val-segmean IoU (%): 63.3 -> 65.4Improved
random placement for segmentation (ablation)BlitzNet300 · VOC12val-segmean IoU (%): 63.3 -> 63.1Hurt
remove object context (objects only in random context) (ablation)single-category detector · VOC12 first 5 categoriesaverage AP (%): 48.7 -> 33.9Hurt
enlarge and reblend objects in same location (right context) (ablation)single-category detector · VOC12 first 5 categoriesaverage AP (%): 48.7 -> 51.6Improved
add context-driven augmentation on COCOBlitzNet300 · COCO val2017 detectionmAP@0.5:0.95 (%): 27.3 -> 28.0Improved
random placement on COCO (ablation)Mask R-CNN · COCO val2017 detectionmAP@0.5:0.95 (%): 38.6 -> 36.9Hurt
add context-driven augmentation with decaying probabilityMask R-CNN · COCO val2017 detectionmAP@0.5:0.95 (%): 38.6 -> 39.1Improved

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