AI Paper Atlas

Research map / Detection and segmentation / CNN features

AdaptIS: Adaptive Instance Selection Network

Konstantin Sofiiuk, Olga Barinova, Anton Konushin

ICCV 2019 · Detection and segmentation › CNN features · approach: Unified panoptic segmentation · 196 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 Relative CoordConv block (ablation)AdaptIS ResNet-50 · Cityscapes valPQ: 53.9 -> 59.0Improved
use Normalized Focal Loss instead of Focal Loss (ablation)AdaptIS ResNet-50 · Cityscapes valPQ: 55.9 -> 59.0Improved
use Normalized Focal Loss instead of BCE (ablation)AdaptIS ResNet-50 · Cityscapes valPQ: 58.7 -> 59.0Improved
scale backbone from ResNet-50 to ResNet-101 (ablation)AdaptIS · Cityscapes valPQ: 59.0 -> 60.6Improved
scale backbone from ResNet-101 to ResNeXt-101 (ablation)AdaptIS · Cityscapes valPQ: 60.6 -> 62.0Improved
scale backbone from ResNet-101 to ResNeXt-101 (ablation)AdaptIS · COCO valPQ: 37.0 -> 42.3Improved
scale backbone from ResNet-50 to ResNeXt-101 (ablation)AdaptIS · Mapillary valPQ: 32.0 -> 35.9Improved
use AdaptIS instead of Mask R-CNN on overlapping objects (ablation)segmentation method · Toy overlapping objectsAP@.9: 5.8% -> 97.5%Improved
use AdaptIS instead of Mask R-CNN on overlapping objects (ablation)segmentation method · Toy overlapping objectsAP@.5: 74.6% -> 99.6%Improved

Later papers that compared with this method

6 later accepted papers report AdaptIS as a baseline in their results tables; 3 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 0 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