AI Paper Atlas

Research map / Detection and segmentation / CNN features

ShapeMask: Learning to Segment Novel Objects by Refining Shape Priors

Weicheng Kuo, Anelia Angelova, Jitendra Malik, Tsung-Yi Lin

ICCV 2019 · Detection and segmentation › CNN features · approach: Boundary-aware instance segmentation · 126 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 shape priors (ablation)ShapeMask (embed only) · VOC->Non-VOCmask AP: 26.2 -> 30.2Improved
add instance embedding (ablation)ShapeMask (shape only) · VOC->Non-VOCmask AP: 26.4 -> 30.2Improved
add shape priors to the plain baseline (ablation)baseline mask decoder · VOC->Non-VOCmask AP: 13.7 -> 26.4Improved
add instance embedding to the plain baseline (ablation)baseline mask decoder · VOC->Non-VOCmask AP: 13.7 -> 26.2Improved
add shape priors (ablation)ShapeMask (embed only) · Non-VOC->VOCmask AP: 29.4 -> 33.3Improved
add instance embedding (ablation)ShapeMask (shape only) · Non-VOC->VOCmask AP: 30.6 -> 33.3Improved
add shape priors to the plain baseline (ablation)baseline mask decoder · fully supervised COCO val2017mask AP: 35.5 -> 36.9Improved
add instance embedding to the plain baseline (ablation)baseline mask decoder · fully supervised COCO val2017mask AP: 35.5 -> 36.7Improved
add both shape priors and instance embedding (ablation)baseline mask decoder · fully supervised COCO val2017mask AP: 35.5 -> 37.2Improved
train with jittered boxes (ablation)ShapeMask · jittered detections at test timemask AP: 34.3 -> 35.7Improved
jitter test-time detections (ablation)Mask R-CNN · COCO mask APmask AP: 36.4 -> 29.0Hurt
jitter test-time detections (ablation)ShapeMask · COCO mask APmask AP: 37.2 -> 34.3Hurt

Later papers that compared with this method

6 later accepted papers report ShapeMask as a baseline in their results tables; 6 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 1 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