AI Paper Atlas

Research map / Detection and segmentation / CNN features

SCNet: Training Inference Sample Consistency for Instance Segmentation

Thang Vu, Haeyong Kang, Chang D. Yoo

AAAI 2021 · Detection and segmentation › CNN features · approach: Joint detection and instance segmentation · 103 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
Use SCNet instead of HTCResNet-50 cascade instance segmentation · COCO test-devmask AP: 38.5 -> 40.2Improved
Use SCNet instead of HTCResNet-101 cascade instance segmentation · COCO test-devmask AP: 39.7 -> 41.3Improved
Use SCNet instead of HTCResNeXt-101 cascade instance segmentation · COCO test-devmask AP: 41.3 -> 42.7Improved
Add effective sample consistency (ablation)Cascade Mask R-CNN with semantic branch · COCO valmask AP: 37.4 -> 38.8Improved
Add effective sample consistency (ablation)Cascade Mask R-CNN with semantic branch · COCO valspeed (fps): 4.5 -> 6.5Improved
Use effective sample consistency rather than naive sample consistency (ablation)Cascade Mask R-CNN · COCO valspeed (fps): 4.5 -> 6.5Improved
Add feature relay (ablation)Mask R-CNN · COCO valmask AP: 35.1 -> 35.7Improved
Add feature relay (ablation)Cascade Mask R-CNN · COCO valmask AP: 37.4 -> 38.0Improved
Add feature relay (ablation)Cascade Mask R-CNN · COCO valspeed (fps): 4.5 -> 4.1Hurt
Add global context (ablation)Cascade Mask R-CNN with sample consistency and feature relay · COCO valmask AP: 39.0 -> 39.8Improved
Increase global context loss weight from 0 to 1 (ablation)SCNet · COCO valmask AP: 39.6 -> 39.6No clear effect
Use global context loss weight 5 instead of 3 (ablation)SCNet · COCO valmask AP: 39.8 -> 39.6Hurt

Later papers that compared with this method

5 later accepted papers report SC-Net as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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