Instance Segmentation
36개 벤치마크 · 논문 2,533편 · 이 태스크의 논문 보기 →
Benchmarks
COCO test-dev
COCO minival
LVIS v1.0 val
Cityscapes val
ADE20K val
Cityscapes test
ARMBench
Occluded COCO
Separated COCO
TBBR
iSAID
BDD100K val
COCO 2017 val
OoDIS
NYUDv2-IS
SUN-RGBD-IS
UIIS
Box-IS
COCO
COCO val2017
COCO-N Medium
Cityscapes
KINS
LDD
LVIS v1.0 test-dev
NYU Depth v2
PartNet
TexBiG 2022 test
TexBiG 2023 test
UAVBillboards
UFBA-425
coco minval
iShape
nuScenes
Most implemented
Mask R-CNN
MMDetection: Open MMLab Detection Toolbox and Benchmark
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
YOLACT: Real-time Instance Segmentation
Deep High-Resolution Representation Learning for Visual Recognition
Deep High-Resolution Representation Learning for Human Pose Estimation
Papers
CedarCypress3D: an annotated UAV-LiDAR dataset of individual trees in planted cedar and cypress forests
Individual tree measurements derived from Light Detection and Ranging (LiDAR) mounted on Unmanned Aerial Vehicles (UAV) provide valuable information for forest inventory, ecosystem monitoring, and sustainable forest mana…
Instance SegmentationSemantic SegmentationPoint CloudsQCell: Recombining and Aligning Cell Queries for Overlapping Instance Segmentation
Instance segmentation of overlapping cells in microscopy remains challenging due to semi-transparent structures that produce weak boundaries and mixed visual evidence in overlap regions. Existing methods address this thr…
Instance SegmentationCell SegmentationQuality Inspection of Printed Circuit Board Pin Insertion via Semantic Segmentation and Board-Level Feature Extraction
Quality control during printed circuit board (PCB) assembly is a critical step in ensuring reliable electronic products. Detecting misaligned pins during or after pin insertion remains a particularly challenging inspecti…
Instance SegmentationSemantic SegmentationAnomaly DetectionHarvestPoint-ACT: Explicit Target Selection and Harvest-Point Conditioning for Robotic Fruit Harvesting under Occlusion
End-to-end imitation learning avoids hand-made robot motion for approaching and grasping, but the policy must still decide which fruit to pick and where to close the gripper. Occlusion can make the policy lose the select…
Instance SegmentationTEAMS: Text-prompted spatiotEmporal dual-heAd Mamba Snake
Deep snake is a promising family of instance segmentation methods that accurately predicts object-level contours, thereby overcoming common pixel-level misclassification issues such as mask cavities and jagged edges in s…
Medical Image SegmentationInstance SegmentationSemantic SegmentationUnsupervised Learning of Cell Instances with Generative Routing Pyramids
Identifying and representing object instances such as cells or nuclei is a common task in microscopy image analysis. Established machine learning workflows typically use supervised detection or segmentation followed by f…
Instance Segmentation