AI Paper Atlas

Research map / Detection and segmentation / CNN features

EfficientPS: Efficient Panoptic Segmentation

Rohit Mohan, Abhinav Valada

IJCV 2021 · Detection and segmentation › CNN features · approach: Unified panoptic segmentation · 270 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
pre-train on Mapillary VistasEfficientPS · Cityscapes val (single-scale)PQ (%): 63.9 -> 66.1Improved
pre-train on Mapillary VistasEfficientPS · Cityscapes val (multi-scale)PQ (%): 65.1 -> 67.5Improved
multi-scale evaluationEfficientPS · Cityscapes valPQ (%): 63.9 -> 65.1Improved
multi-scale evaluationEfficientPS · Mapillary Vistas valPQ (%): 38.3 -> 40.5Improved
multi-scale evaluationEfficientPS · KITTI valPQ (%): 42.9 -> 43.7Improved
pre-train on Mapillary VistasEfficientPS · Cityscapes testPQ (%): 64.1 -> 67.1Improved
use EfficientPS instead of Panoptic-Deeplabpanoptic segmentation model · Cityscapes val (single-scale, no pre-training)PQ (%): 63.0 -> 63.9Improved
use EfficientPS instead of Panoptic-Deeplabpanoptic segmentation model · Cityscapes test (no pre-training)PQ (%): 62.3 -> 64.1Improved
use EfficientPS instead of Seamlesspanoptic segmentation model · Cityscapes efficiencyparameters and time: 51.43 -> 40.89 M params; 168 -> 166 msImproved
use EfficientPS instead of Panoptic-Deeplabpanoptic segmentation model · KITTI/Vistas efficiencyFLOPs: 547.49 -> 433.94 GFLOPsImproved

Later papers that compared with this method

1 later accepted paper reports EfficientPS as a baseline in their results tables; 1 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 3 of 3 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