AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

Better Call SAL: Towards Learning to Segment Anything in Lidar

Aljosa Osep, Tim Meinhardt, Francesco Ferroni, Neehar Peri, Deva Ramanan, Laura Leal-Taixé

ECCV 2024 · Vision-language and multimodal › CLIP and zero-shot · approach: Adapting VLMs for zero-shot classification · 30 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
remove unlabeled points from pseudo-labeled clouds during training (ablation)SAL · SemanticKITTI class-agnosticPQ: 22.2 -> 59.3Improved
add FrankenFrustum augmentation (ablation)SAL · SemanticKITTI class-agnosticPQ: 59.3 -> 62.5Improved
mix point clouds from different scans in FrankenFrustum (ablation)SAL · SemanticKITTI class-agnosticPQ: 62.5 -> 62.8Improved
increase decoder queries from 100 to 300 with pseudo labels (ablation)SAL · SemanticKITTI class-agnosticPQ: 53.9 -> 62.8Improved
increase queries with GT labels (ablation)SAL · SemanticKITTI stuff classesPQ St: +0.5No clear effect
scale pseudo-labeled data (add test set to train) (ablation)SAL · SemanticKITTIPQ: +2.5 PQImproved
add CLIP token distillation loss (ablation)SAL · SemanticKITTI linear probingPQ: 20.0 -> 33.1Improved
erode SAM masks in image domain (ablation)SAM unprojection baseline · SemanticKITTI class-agnosticPQ: 46.0 -> 42.2Hurt
filter SAM masks by DBSCAN overlap (ablation)SAM unprojection baseline · SemanticKITTI class-agnosticPQ: PQ Th +27.1, PQ St -18.6, overall 46.7Mixed
replace SAM masks with DBSCAN clusters when overlap is large (ablation)SAM unprojection baseline · SemanticKITTI class-agnosticPQ: +3.9 (to 48.7)Improved
distill lifted CLIP features into a Lidar model instead of lifting at inferenceSAM+DBS+CLIP · SemanticKITTI zero-shot LPSPQ: 27.5 -> 33.1Improved
prompt with super classes instead of default classesSAL zero-shot · SemanticKITTIPQ: 24.8 -> 48.5Improved

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