AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

High Quality Entity Segmentation

Lu Qi, Jason Kuen, Tiancheng Shen, Jiuxiang Gu, Wenbo Li, Weidong Guo, Jiaya Jia, Zhe Lin, Ming-Hsuan Yang

ICCV 2023 · Detection and segmentation › Open-set and few-shot detection · approach: Interactive and referring segmentation · 79 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
fuse full image and high-res crops with CropFormerMask2Former · EntitySeg entity segmentationAP^e: 39.5 -> 41.0Improved
increase Mask2Former input resolution to (2700,4500)Mask2Former · EntitySeg entity segmentationAP^e: 39.5 -> 40.6Mixed
add CropFormer on longer training schedulesMask2Former · EntitySeg entity segmentationAP^e: 40.9 -> 42.8Improved
use both full image and crop predictions (B-OC) instead of crops only (B-C) (ablation)CropFormer decoder · EntitySeg entity segmentationAP^e: 40.2 -> 41.0Improved
use batch decoder crops (B-C) instead of full image (I-O) (ablation)CropFormer decoder · EntitySeg entity segmentationAP^e: 39.3 -> 40.2Improved
use crop ratio 0.7 instead of 0.5 (ablation)CropFormer · EntitySeg entity segmentationAP^e: 38.5 -> 41.0Improved
use crop ratio 0.8 instead of 0.7 (ablation)CropFormer · EntitySeg entity segmentationAP^e: 41.0 -> 40.9No clear effect
use fixed 4 corner crops instead of random crops in training (ablation)CropFormer · EntitySeg entity segmentationAP^e: 39.7 -> 41.0Improved
test with 8 fixed crops instead of 4 (trained with 4) (ablation)CropFormer · EntitySeg entity segmentationAP^e: 41.0 -> 41.3Improved
add self-attention and FFN to association module cross-attention (ablation)CropFormer · EntitySeg entity segmentationAP^e: 40.7 -> 41.0Improved
add CropFormer to Mask2Former on COCO instance segmentationMask2Former · COCO instance segmentationAP: 50.1 -> 51.9Improved
add CropFormer to Mask2Former on ADE20K panoptic segmentationMask2Former · ADE20K panopticPQ: 48.1 -> 49.7Improved

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