AI Paper Atlas

Research map / Detection and segmentation / CNN features

The Surprising Impact of Mask-Head Architecture on Novel Class Segmentation

Vighnesh Birodkar, Zhichao Lu, Siyang Li, Vivek Rathod, Jonathan Huang

ICCV 2021 · Detection and segmentation › CNN features · approach: Boundary-aware instance segmentation · 29 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
train mask-head with only groundtruth boxes instead of proposals+GT (ablation)Mask R-CNN ResNet-50-FPN · COCO Non-VOCmask mAP: 18.2 -> 25.9Improved
train mask-head with only groundtruth boxes instead of proposals+GT (ablation)Mask R-CNN ResNet-101-FPN · COCO Non-VOCmask mAP: 19.6 -> 29.3Improved
replace ResNet-4 mask-head with Hourglass-52 (ablation)Deep-MARC ResNet-101-FPN · COCO Non-VOCmask mAP: 27.4 -> 34.4Improved
replace ResNet-4 mask-head with Hourglass-52 (ablation)Deep-MARC ResNet-101-FPN · COCO VOC (seen)mask mAP: 40.3 -> 41.9No clear effect
replace ResNet-4 with Hourglass-52 when training with proposals+GT (ablation)Deep-MARC · COCO Non-VOCmask mAP: 21.0 -> 20.6No clear effect
increase Hourglass mask-head depth from 10 to 20 (ablation)Deep-MAC Hourglass-104 · COCO Non-VOCmask mAP: 29.4 -> 32.5Improved
replace ResNet-4 with Hourglass-52 mask-head, detection-free (ablation)Deep-MAC · COCO Non-VOCmIOU: 62.1 -> 79.2Improved
add long range skip connections to Hourglass-20 (ablation)Deep-MAC HG-20 · COCO Non-VOCmask mAP: 31.7 -> 32.2Improved
add encoder-decoder structure to Hourglass-20 (ablation)Deep-MAC HG-20 · COCO Non-VOCmask mAP: 29.2 -> 32.2Improved
replace 20 convs with dilated convs in ResNet-20 mask-head (ablation)Deep-MAC ResNet-20 · COCO Non-VOCmask mAP: 29.9 -> 30.7Improved
put hourglass depth in the mask-head instead of shared backbone (ablation)Deep-MAC · COCO Non-VOC, GT boxesmIOU: 68.8 -> 77.8Improved
replace Hourglass-52 mask-head with 4 fully connected layers (ablation)Deep-MAC · COCO Non-VOCmask mAP: 32.5 -> 28.2Hurt

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