AI Paper Atlas

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

Primitive Generation and Semantic-Related Alignment for Universal Zero-Shot Segmentation

Shuting He, Henghui Ding, Wei Jiang

CVPR 2023 · Detection and segmentation › Open-set and few-shot detection · approach: Zero-shot segmentation and detection · 31 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
Replace the GMMN generator with a primitive generator (ablation)Zero-shot panoptic segmentation model · MSCOCO zero-shot panoptic segmentationHM PQ: at least 9.0% PQImproved
Add semantic relationship alignment (ablation)Primitive generator · MSCOCO zero-shot panoptic segmentationHM PQ: 2.6%Improved
Add feature disentanglement to alignment (ablation)Primitive generator with alignment · MSCOCO zero-shot panoptic segmentationHM PQ: 2.0% HM-PQImproved
Add feature disentanglement to alignment (ablation)Primitive generator with alignment · MSCOCO zero-shot panoptic segmentationHM SQ: 13.3% HM-SQImproved
Add feature disentanglement to alignment (ablation)Primitive generator with alignment · MSCOCO zero-shot panoptic segmentationHM RQ: 2.7% HM-RQImproved
Increase primitives from 100 to 400 (ablation)Primitive generator · MSCOCO zero-shot panoptic segmentationPQ: 4.2%Improved
Increase primitives beyond 400 (ablation)Primitive generator · MSCOCO zero-shot panoptic segmentationPQHurt
Use primitive generation, relationship alignment, and disentanglement instead of a GMMN generator (ablation)Zero-shot panoptic segmentation model · MSCOCO zero-shot panoptic segmentationHM PQ: 8.7 -> 22.3Improved
Use primitive generation, relationship alignment, and disentanglement instead of a projection-based classifier (ablation)Zero-shot panoptic segmentation model · MSCOCO zero-shot panoptic segmentationunseen PQ: 0.0 -> 15.3Improved
Use PADing instead of ZegFormer-segZero-shot semantic segmentation · COCO-StuffHM IoU: 3.5% HM-IoUImproved
Use PADing instead of ZSIZero-shot instance segmentation · GZSI 48/17HM mAP: 7.20% HM-mAPImproved
Use PADing instead of ZSIZero-shot instance segmentation · GZSI 48/17HM Recall: 5.27% HM-RecallImproved

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