AI Paper Atlas

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

SOS: Segment Object System for Open-World Instance Segmentation With Object Priors

Christian Wilms, Tim Rolff, Maris N Hillemann, Robert Johanson, Simone Frintrop

ECCV 2024 · Detection and segmentation › Open-set and few-shot detection · approach: Amodal and open-world instance segmentation · 1 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 Grid prompts with DINO self-attention object prior for SAM (ablation)SOS · COCO (VOC) -> COCO (non-VOC)F1: 6.2 -> 14.3Improved
add SAM-generated pseudo annotations with Grid prior (ablation)class-agnostic Mask R-CNN · COCO (VOC) -> COCO (non-VOC)F1: 2.2 -> 6.2Improved
add confidence thresholding and NMS post-processing of pseudo annotations (ablation)SOS with DINO prior · COCO (VOC) -> COCO (non-VOC)F1: 14.3 -> 14.4Improved
use up to 10 instead of 3 pseudo annotations per image (ablation)SOS · COCO (VOC) -> COCO (non-VOC)F1: 13.4 -> 14.4Improved
increase pseudo annotations from 10 to 20 (ablation)SOS · COCO (VOC) -> COCO (non-VOC)F1: 14.4 -> 14.3No clear effect
use learned (CAM, DeepGaze) priors instead of simple ones (Spx, Contour, VOCUS2) (ablation)SOS object prior · COCO (VOC) -> COCO (non-VOC)F1: 9.4 vs 9.6-10.5No clear effect
use SOS instead of GGN pseudo-annotation OWISMask R-CNN training · COCO (VOC) -> COCO (non-VOC)F1: 8.4 -> 14.5Improved
use SOS instead of vanilla SAMopen-world instance segmentation · COCO (VOC) -> COCO (non-VOC)F1: 6.7 -> 14.5Improved
use SOS instead of LDETopen-world instance segmentation · COCO -> UVOF1: 28.5 -> 28.0Hurt
use SOS instead of GGNopen-world instance segmentation · COCO -> ADE20kF1: 13.3 -> 17.0Improved
use SOS pseudo annotations instead of GGNpseudo annotation quality · COCO train non-VOCprecision: 7.3 -> 19.0Improved

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