SOTAVerified

Instance Segmentation

Instance Segmentation is a computer vision task that involves identifying and separating individual objects within an image, including detecting the boundaries of each object and assigning a unique label to each object. The goal of instance segmentation is to produce a pixel-wise segmentation map of the image, where each pixel is assigned to a specific object instance.

Image Credit: Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers, CVPR'21

Papers

Showing 251300 of 2262 papers

TitleStatusHype
Continual Learning for Image Segmentation with Dynamic QueryCode1
Unleashing the Power of Prompt-driven Nucleus Instance SegmentationCode1
Low Latency Instance Segmentation by Continuous Clustering for LiDAR SensorsCode1
HoVer-UNet: Accelerating HoVerNet with UNet-based multi-class nuclei segmentation via knowledge distillationCode1
Video Instance MattingCode1
Audio-Visual Instance SegmentationCode1
Instance Segmentation under Occlusions via Location-aware Copy-Paste Data AugmentationCode1
A Deep Learning Approach to Teeth Segmentation and Orientation from Panoramic X-raysCode1
Label-efficient Segmentation via Affinity PropagationCode1
RoboLLM: Robotic Vision Tasks Grounded on Multimodal Large Language ModelsCode1
Unsupervised Learning of Object-Centric Embeddings for Cell Instance Segmentation in Microscopy ImagesCode1
Relational Prior Knowledge Graphs for Detection and Instance SegmentationCode1
EViT: An Eagle Vision Transformer with Bi-Fovea Self-AttentionCode1
Zero-Shot Refinement of Buildings' Segmentation Models using SAMCode1
PharmacoNet: Accelerating Large-Scale Virtual Screening by Deep Pharmacophore ModelingCode1
Mask4Former: Mask Transformer for 4D Panoptic SegmentationCode1
MoCaE: Mixture of Calibrated Experts Significantly Improves Object DetectionCode1
3D Indoor Instance Segmentation in an Open-WorldCode1
ClusterFormer: Clustering As A Universal Visual LearnerCode1
MosaicFusion: Diffusion Models as Data Augmenters for Large Vocabulary Instance SegmentationCode1
NeuralLabeling: A versatile toolset for labeling vision datasets using Neural Radiance FieldsCode1
OmniLRS: A Photorealistic Simulator for Lunar RoboticsCode1
TreeLearn: A deep learning method for segmenting individual trees from ground-based LiDAR forest point cloudsCode1
X-PDNet: Accurate Joint Plane Instance Segmentation and Monocular Depth Estimation with Cross-Task Distillation and Boundary CorrectionCode1
Nucleus-aware Self-supervised Pretraining Using Unpaired Image-to-image Translation for Histopathology ImagesCode1
Panoptic Vision-Language Feature FieldsCode1
Fully Automated Scan-to-BIM Via Point Cloud Instance SegmentationCode1
Towards Content-based Pixel Retrieval in Revisited Oxford and ParisCode1
Mask-Attention-Free Transformer for 3D Instance SegmentationCode1
Ref-Diff: Zero-shot Referring Image Segmentation with Generative ModelsCode1
Learning to Upsample by Learning to SampleCode1
1st Place Solution for the 5th LSVOS Challenge: Video Instance SegmentationCode1
Real-time Automatic M-mode Echocardiography Measurement with Panel Attention from Local-to-Global PixelsCode1
A One Stop 3D Target Reconstruction and multilevel Segmentation MethodCode1
SegPrompt: Boosting Open-world Segmentation via Category-level Prompt LearningCode1
FoodSAM: Any Food SegmentationCode1
Pseudo-label Alignment for Semi-supervised Instance SegmentationCode1
NuInsSeg: A Fully Annotated Dataset for Nuclei Instance Segmentation in H&E-Stained Histological ImagesCode1
LiDAR-Camera Panoptic Segmentation via Geometry-Consistent and Semantic-Aware AlignmentCode1
Guided Distillation for Semi-Supervised Instance SegmentationCode1
UGainS: Uncertainty Guided Anomaly Instance SegmentationCode1
Synthetic Instance Segmentation from Semantic Image Segmentation MasksCode1
Unmasking Anomalies in Road-Scene SegmentationCode1
GaPro: Box-Supervised 3D Point Cloud Instance Segmentation Using Gaussian Processes as Pseudo LabelersCode1
CTVIS: Consistent Training for Online Video Instance SegmentationCode1
Learning Dynamic Query Combinations for Transformer-based Object Detection and SegmentationCode1
On Point Affiliation in Feature UpsamplingCode1
CalibNet: Dual-branch Cross-modal Calibration for RGB-D Salient Instance SegmentationCode1
SynTable: A Synthetic Data Generation Pipeline for Unseen Object Amodal Instance Segmentation of Cluttered Tabletop ScenesCode1
AnyStar: Domain randomized universal star-convex 3D instance segmentationCode1
Show:102550
← PrevPage 6 of 46Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1InternImage-HAP5080.8Unverified
2ResNeSt-200 (multi-scale)AP5070.2Unverified
3CenterMask + VoVNetV2-99 (multi-scale)AP5066.2Unverified
4CenterMask + VoVNetV2-57 (single-scale)AP5060.8Unverified
5Co-DETRmask AP57.1Unverified
6CBNetV2 (EVA02, single-scale)mask AP56.1Unverified
7ISDA (ResNet-50)APL55.7Unverified
8EVAmask AP55.5Unverified
9FD-SwinV2-Gmask AP55.4Unverified
10Mask Frozen-DETRmask AP55.3Unverified
#ModelMetricClaimedVerifiedStatus
1InternImage-BGFLOPs501Unverified
2Co-DETRmask AP56.6Unverified
3ViT-CoMer-L (Mask RCNN, DINOv2)mask AP55.9Unverified
4InternImage-Hmask AP55.4Unverified
5EVAmask AP55Unverified
6Mask Frozen-DETRmask AP54.9Unverified
7MasK DINO (SwinL, multi-scale)mask AP54.5Unverified
8ViT-Adapter-L (HTC++, BEiTv2, O365, multi-scale)mask AP54.2Unverified
9GLEE-Promask AP54.2Unverified
10SwinV2-G (HTC++)mask AP53.7Unverified