AI Paper Atlas

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

ViewCo: Discovering Text-Supervised Segmentation Masks via Multi-View Semantic Consistency

Pengzhen Ren, Changlin Li, Hang Xu, Yi Zhu, Guangrun Wang, Jianzhuang Liu, Xiaojun Chang, Xiaodan Liang

ICLR 2023 · Detection and segmentation › Open-set and few-shot detection · approach: Interactive and referring segmentation · 16 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 ViewCo instead of GroupViT, pretrained on CC12M+YFCCGroupViT · COCO Stuff valmIoU: 20.9 -> 23.5Improved
use ViewCo instead of GroupViT, pretrained on CC12MGroupViT · PASCAL VOC 2012 valmIoU: 41.1 -> 45.7Improved
use ViewCo instead of GroupViT, pretrained on CC12M+YFCCGroupViT · PASCAL Context valmIoU: 22.3 -> 23.0Improved
add an image-level visual self-supervision module (ablation)GroupViT · COCO StuffmIoU: 18.4 -> 18.6Improved
add cross-view semantic-level contrast instead of image-level contrast (ablation)GroupViT+ · COCO StuffmIoU: 18.6 -> 19.1Improved
add multi-view vision-language contrast instead of single-view contrast (ablation)GroupViT+ · COCO StuffmIoU: 18.6 -> 19.7 (+1.1)Improved
add multi-view vision-language contrast instead of single-view contrast (ablation)ViewCo · COCO StuffmIoU: 19.1 -> 20.6 (+1.5)Improved
use ViewCo instead of GroupViTGroupViT · ImageNet zero-shotAcc@1: 42.9 -> 46.3Improved

Later papers that compared with this method

2 later accepted papers report ViewCo as a baseline in their results tables; 2 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 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