AI Paper Atlas

Research map / Detection and segmentation / CNN features

Associative Embedding: End-to-End Learning for Joint Detection and Grouping

NeurIPS 2017 · Detection and segmentation › CNN features · approach: Joint detection and instance segmentation · 554 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 multi-scale evaluation to single-scale inference (ablation)Associative Embedding · MS-COCO test-devAP: 0.566 -> 0.630Helped
Add single-person pose refinement to single-scale inference (ablation)Associative Embedding · MS-COCO test-devAP: 0.566 -> 0.628Helped
Add single-person pose refinement to multi-scale inference (ablation)Associative Embedding · MS-COCO test-devAP: 0.630 -> 0.655Helped
Replace predicted detections with ground-truth detections while keeping predicted tags (ablation)Associative Embedding · MS-COCO held-out 500 training imagesAP: 59.2 -> 94.0Helped
Use associative embedding for instance segmentationStacked hourglass · PASCAL VOC 2012 val, IOU=0.5 and IOU=0.7mAP: 35.1 at IOU=0.5; 26.0 at IOU=0.7, compared with MNC 63.5 and 41.5Mixed

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