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 751800 of 2262 papers

TitleStatusHype
Fashionpedia: Ontology, Segmentation, and an Attribute Localization DatasetCode1
Fast and Efficient Transformer-based Method for Bird's Eye View Instance PredictionCode1
CEDNet: A Cascade Encoder-Decoder Network for Dense PredictionCode1
Faster Mean-shift: GPU-accelerated clustering for cosine embedding-based cell segmentation and trackingCode1
Real-time Automatic M-mode Echocardiography Measurement with Panel Attention from Local-to-Global PixelsCode1
MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision ModelsCode1
Real-time Instance Segmentation with Discriminative Orientation MapsCode1
MobileViG: Graph-Based Sparse Attention for Mobile Vision ApplicationsCode1
GAInS: Gradient Anomaly-aware Biomedical Instance SegmentationCode1
The Endoscapes Dataset for Surgical Scene Segmentation, Object Detection, and Critical View of Safety Assessment: Official Splits and BenchmarkCode1
CHEX: CHannel EXploration for CNN Model CompressionCode1
FcaNet: Frequency Channel Attention NetworksCode1
CholecInstanceSeg: A Tool Instance Segmentation Dataset for Laparoscopic SurgeryCode1
MosaicFusion: Diffusion Models as Data Augmenters for Large Vocabulary Instance SegmentationCode1
Instance Semantic Segmentation Benefits from Generative Adversarial NetworksCode1
MosaicOS: A Simple and Effective Use of Object-Centric Images for Long-Tailed Object DetectionCode1
Decoupling Classifier for Boosting Few-shot Object Detection and Instance SegmentationCode1
GaPro: Box-Supervised 3D Point Cloud Instance Segmentation Using Gaussian Processes as Pseudo LabelersCode1
Large-scale 6D Object Pose Estimation Dataset for Industrial Bin-PickingCode1
FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular CamerasCode1
CISCA and CytoDArk0: a Cell Instance Segmentation and Classification method for histo(patho)logical image Analyses and a new, open, Nissl-stained dataset for brain cytoarchitecture studiesCode1
Recurrence along Depth: Deep Convolutional Neural Networks with Recurrent Layer AggregationCode1
Fine-Grained Vehicle Perception via 3D Part-Guided Visual Data AugmentationCode1
FinnWoodlands DatasetCode1
DCT-Mask: Discrete Cosine Transform Mask Representation for Instance SegmentationCode1
FipTR: A Simple yet Effective Transformer Framework for Future Instance Prediction in Autonomous DrivingCode1
Classification Calibration for Long-tail Instance SegmentationCode1
NDD20: A large-scale few-shot dolphin dataset for coarse and fine-grained categorisationCode1
A Weakly Supervised Amodal Segmenter with Boundary Uncertainty EstimationCode1
1st Place Solution for the 5th LSVOS Challenge: Video Instance SegmentationCode1
FoodSAM: Any Food SegmentationCode1
Classifying Breast Histopathology Images with a Ductal Instance-Oriented PipelineCode1
FsaNet: Frequency Self-attention for Semantic SegmentationCode1
Forest R-CNN: Large-Vocabulary Long-Tailed Object Detection and Instance SegmentationCode1
Class-incremental Continual Learning for Instance Segmentation with Image-level Weak SupervisionCode1
Towards Accurate Post-training Network Quantization via Bit-Split and StitchingCode1
AutoSweep: Recovering 3D Editable Objectsfrom a Single PhotographCode1
FourierNet: Compact mask representation for instance segmentation using differentiable shape decodersCode1
Fully Automated Scan-to-BIM Via Point Cloud Instance SegmentationCode1
Nuclei Segmentation via a Deep Panoptic Model with Semantic Feature FusionCode1
CLIP-VIS: Adapting CLIP for Open-Vocabulary Video Instance SegmentationCode1
NucMM Dataset: 3D Neuronal Nuclei Instance Segmentation at Sub-Cubic Millimeter ScaleCode1
FreePoint: Unsupervised Point Cloud Instance SegmentationCode1
NuClick: A Deep Learning Framework for Interactive Segmentation of Microscopy ImagesCode1
Algorithm-hardware Co-design for Deformable ConvolutionCode1
NuInsSeg: A Fully Annotated Dataset for Nuclei Instance Segmentation in H&E-Stained Histological ImagesCode1
ClusterFormer: Clustering As A Universal Visual LearnerCode1
Towards unconstrained joint hand-object reconstruction from RGB videosCode1
Auto-Panoptic: Cooperative Multi-Component Architecture Search for Panoptic SegmentationCode1
Fully Sparse Fusion for 3D Object DetectionCode1
Show:102550
← PrevPage 16 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