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 376400 of 2262 papers

TitleStatusHype
CEDNet: A Cascade Encoder-Decoder Network for Dense PredictionCode1
A Comparative Evaluation of Deep Learning Techniques for Photovoltaic Panel Detection from Aerial ImagesCode1
DVIS++: Improved Decoupled Framework for Universal Video SegmentationCode1
ASF-YOLO: A Novel YOLO Model with Attentional Scale Sequence Fusion for Cell Instance SegmentationCode1
CHEX: CHannel EXploration for CNN Model CompressionCode1
CholecInstanceSeg: A Tool Instance Segmentation Dataset for Laparoscopic SurgeryCode1
MosaicOS: A Simple and Effective Use of Object-Centric Images for Long-Tailed Object DetectionCode1
DVIS: Decoupled Video Instance Segmentation FrameworkCode1
Conformer: Local Features Coupling Global Representations for Visual RecognitionCode1
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
Continuous Copy-Paste for One-Stage Multi-Object Tracking and SegmentationCode1
DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic ConvolutionCode1
Classification Calibration for Long-tail Instance SegmentationCode1
DropIT: Dropping Intermediate Tensors for Memory-Efficient DNN TrainingCode1
Classifying Breast Histopathology Images with a Ductal Instance-Oriented PipelineCode1
Container: Context Aggregation NetworkCode1
Class-incremental Continual Learning for Instance Segmentation with Image-level Weak SupervisionCode1
Human Instance Matting via Mutual Guidance and Multi-Instance RefinementCode1
Humans need not label more humans: Occlusion Copy & Paste for Occluded Human Instance SegmentationCode1
CLIP-VIS: Adapting CLIP for Open-Vocabulary Video Instance SegmentationCode1
DropLoss for Long-Tail Instance SegmentationCode1
DynaMask: Dynamic Mask Selection for Instance SegmentationCode1
ClusterFormer: Clustering As A Universal Visual LearnerCode1
Eigencontours: Novel Contour Descriptors Based on Low-Rank ApproximationCode1
DocSegTr: An Instance-Level End-to-End Document Image Segmentation TransformerCode1
Show:102550
← PrevPage 16 of 91Next →

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