AI Paper Atlas

Research map / Detection and segmentation / 3D detection and driving

Contrastive Lift: 3D Object Instance Segmentation by Slow-Fast Contrastive Fusion

Yash Sanjay Bhalgat, Iro Laina, Joao F. Henriques, Andrea Vedaldi, Andrew Zisserman

NeurIPS 2023 · Detection and segmentation › 3D detection and driving · approach: 3D objectness and scene segmentation · 11 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 slow-fast (EMA teacher) scheme to vanilla contrastive loss (ablation)Contrastive Lift · Messy Rooms (avg)PQ scene: 63.2 -> 66.5Improved
add concentration loss to slow-fast loss (ablation)Contrastive Lift · Messy Rooms (avg)PQ scene: 66.5 -> 69.0Improved
add concentration loss to slow-fast loss (ablation)Contrastive Lift · ScanNet (avg)PQ scene: 61.3 -> 62.0Improved
add slow-fast scheme to vanilla contrastive loss (ablation)Contrastive Lift · ScanNet (avg)PQ scene: 60.5 -> 61.3Improved
add concentration loss to vanilla contrastive without slow field (ablation)Contrastive Lift vanilla · Messy Rooms (avg)PQ scene: 63.2 -> 51.7Hurt
add concentration loss to vanilla contrastive without slow field (ablation)Contrastive Lift vanilla · ScanNet (avg)PQ scene: 60.5 -> 55.2Hurt
replace Panoptic Lifting linear assignment with slow-fast contrastive liftingPanopLi · Messy Rooms Old Room 500 objectsPQ scene: 51.0 -> 55.0Improved
replace linear assignment with slow-fast contrastive liftingPanopLi · ScanNetPQ scene: 58.9 -> 62.3Improved
vanilla contrastive loss instead of linear assignmentPanopLi · ReplicaPQ scene: 57.9 -> 57.8No clear effect
lift 2D Mask2Former segments to 3D with Contrastive LiftMask2Former · ScanNetPQ (per frame): 42.0 -> 61.6Improved
replace HDBSCAN with DBSCAN clustering (ablation)Contrastive Lift · ScanNetPQ scene: 62.0 -> 61.8No clear effect
replace contrastive loss with DINO-style loss (ablation)Contrastive Lift · ScanNetPQ scene: 60.5 -> 54.7Hurt

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