AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

RankSeg: Adaptive Pixel Classification with Image Category Ranking for Segmentation

Haodi He, Yuhui Yuan, Xiangyu Yue, Han Hu

ECCV 2022 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 17 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 RankSeg (multi-label head, label selection, rank-adaptive temperature)Mask2Former Swin-L · ADE20K panopticPQ: 48.1 -> 48.9Improved
add multi-task multi-label classification only (ablation)Segmenter ViT-B · COCO-StuffmIoU: 41.85 -> 42.38Improved
add multi-task multi-label classification only (ablation)Segmenter ViT-B · ADE20K-FullmIoU: 17.93 -> 17.81No clear effect
add label sorting and selection to MT (ablation)Segmenter ViT-B · COCO-StuffmIoU: 42.38 -> 44.31Improved
add rank-adaptive temperature instead of shared temperature (ablation)Segmenter ViT-B · COCO-StuffmIoU: 44.31 -> 44.98Improved
add rank-adaptive temperature instead of shared temperature (ablation)Segmenter ViT-B · VSPWmIoU: 59.6 -> 60.1Improved
use more accurate multi-label predictor (ResNet101 to Swin-L Query2Label) (ablation)Segmenter ViT-B · COCO-StuffmIoU: 39.34 -> 44.42Improved
use joint multi-task instead of independent single-task scheme (ablation)Segmenter ViT-B · COCO-StuffmIoU: 44.42 -> 44.98Improved
increase selected label count kappa from 50 to 171 (all labels) (ablation)Segmenter ViT-B · COCO-StuffmIoU: 44.98 -> 44.20Hurt
increase multi-label loss weight from 10 to 20 (ablation)Segmenter ViT-B · COCO-StuffmIoU: 44.98 -> 44.04Hurt
use 1x transformer encoder head instead of GAP+Linear for multi-label prediction (ablation)Segmenter ViT-B · COCO-StuffmIoU: 43.19 -> 44.98Improved
derive multi-label predictions from segmentation output (mAP 58.55) (ablation)Segmenter ViT-B · COCO-StuffmIoUNo clear effect

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