AI Paper Atlas

Research map / Detection and segmentation / CNN features

BlitzNet: A Real-Time Deep Network for Scene Understanding

Nikita Dvornik, Konstantin Shmelkov, Julien Mairal, Cordelia Schmid

ICCV 2017 · Detection and segmentation › CNN features · approach: Joint detection and instance segmentation · 216 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 joint segmentation training to detection (ablation)BlitzNet300 · VOC12 val-segdetection mAP (%): 78.9 -> 80.0Improved
add joint detection training to segmentation (ablation)BlitzNet300 · VOC12 val-segsegmentation mIoU (%): 72.4 -> 72.8Improved
add extra detection-only images (VOC07 trainval) to joint training (ablation)BlitzNet300 · VOC12 val-segsegmentation mIoU (%): 72.4 -> 75.7Improved
add extra detection-only images (VOC07 trainval) to joint training (ablation)BlitzNet300 · VOC12 val-segdetection mAP (%): 83.0 -> 83.6Improved
add joint segmentation training (ablation)BlitzNet512 · COCO minival2014detection mAP (%): 33.2 -> 34.1Improved
add joint detection training (ablation)BlitzNet512 · COCO minival2014segmentation mIoU (%): 48.3 -> 53.5Improved
add segmentation training to stride-4 model (ablation)BlitzNet300 (s4) · VOC07 testmAP (%): 78.2 -> 79.1Improved
add segmentation training to stride-8 model (ablation)BlitzNet512 (s8) · VOC07 testmAP (%): 80.7 -> 81.5Improved
use upscale-stream stride 4 instead of 8 (ablation)BlitzNet300 · VOC07 testmAP (%): 78.5 -> 78.2No clear effect
pretrain on COCOBlitzNet512 · VOC12 testmAP (%): 79.0 -> 83.8Improved
use ResSkip instead of hourglass-style fusion block (ablation)BlitzNet · VOC07 test / VOC12 valmAP and mIoU (%): 78.7 -> 79.1Improved
use ResSkip instead of refine-style fusion block (ablation)BlitzNet · VOC07 test / VOC12 valmAP and mIoU (%): 78.0 -> 79.1Mixed

Later papers that compared with this method

1 later accepted paper reports BlitzNet300 as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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