AI Paper Atlas

Research map / Detection and segmentation / CNN features

SSAP: Single-Shot Instance Segmentation With Affinity Pyramid

Naiyu Gao, Yanhu Shan, Yupei Wang, Xin Zhao, Yinan Yu, Ming Yang, Kaiqi Huang

ICCV 2019 · Detection and segmentation › CNN features · approach: Boundary-aware instance segmentation · 230 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 cascaded graph partition initialized from 1/16 resolution (ablation)SSAP graph partition · Cityscapes valAP (%): 28.9 -> 31.5Improved
initialize cascade from 1/64 instead of 1/16 (ablation)SSAP graph partition · Cityscapes valAP (%): 31.5 -> 30.9Hurt
add joint learning with hierarchical affinity pyramid (ablation)SSAP · Cityscapes valAP (%): 30.0 -> 31.3Improved
add joint learning with affinity (r=5) to semantic segmentation (ablation)SSAP · Cityscapes valmIoU (%): 74.5 -> 75.0Improved
add joint learning to single-scale features without dilation (ablation)SSAP · Cityscapes valmIoU (%): 74.5 -> 74.2Hurt
add joint learning to single-scale features with dilation (ablation)SSAP · Cityscapes valAP (%): 30.6 -> 30.8Improved
enlarge affinity window from r=5 to r=9 (ablation)SSAP · Cityscapes valAP (%): 31.3 -> 30.0Hurt
add long-range affinities A2 to A5 to A1 (ablation)SSAP · Cityscapes valAP (%): 25.7 -> 31.5Improved
add balanced training data by dropping 80% all-1 pixels (ablation)SSAP · Cityscapes valAP (%): 29.1 -> 30.0Improved
add 3x affinity loss on object pixels (ablation)SSAP · Cityscapes valAP (%): 30.0 -> 31.3Improved
use kernel size 5 instead of 3 (ablation)SSAP · Cityscapes valAP (%): 31.3 -> 31.5Improved
add segmentation refinement (ablation)SSAP ResNet-50 · Cityscapes valAP (%): 28.7 -> 31.5Improved

Later papers that compared with this method

7 later accepted papers report SSAP as a baseline in their results tables; 5 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 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