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 551575 of 2262 papers

TitleStatusHype
Union-over-Intersections: Object Detection beyond Winner-Takes-AllCode0
Quantification of cardiac capillarization in single-immunostained myocardial slices using weakly supervised instance segmentation0
Continual Learning for Image Segmentation with Dynamic QueryCode1
SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose EstimationCode2
Unified Batch Normalization: Identifying and Alleviating the Feature Condensation in Batch Normalization and a Unified Framework0
Unleashing the Power of Prompt-driven Nucleus Instance SegmentationCode1
Multi-task Planar Reconstruction with Feature Warping GuidanceCode0
Adapter is All You Need for Tuning Visual TasksCode2
Text and Click inputs for unambiguous open vocabulary instance segmentationCode0
Understanding Self-Supervised Features for Learning Unsupervised Instance Segmentation0
ZeroPS: High-quality Cross-modal Knowledge Transfer for Zero-Shot 3D Part Segmentation0
Low Latency Instance Segmentation by Continuous Clustering for LiDAR SensorsCode1
Deep learning-based instance segmentation for the precise automated quantification of digital breast cancer immunohistochemistry images0
HoVer-UNet: Accelerating HoVerNet with UNet-based multi-class nuclei segmentation via knowledge distillationCode1
GP-NeRF: Generalized Perception NeRF for Context-Aware 3D Scene Understanding0
ToSkA: Topological Skeleton Analysis for Network-Based Shape Representation and Evaluation of Objects from Cells to Death Stars0
Self-trained Panoptic Segmentation0
VertDetect: Fully End-to-End 3D Vertebral Instance Segmentation Model0
PWISeg: Point-based Weakly-supervised Instance Segmentation for Surgical InstrumentsCode0
3DFusion, A real-time 3D object reconstruction pipeline based on streamed instance segmented data0
SeaTurtleID2022: A long-span dataset for reliable sea turtle re-identification0
SKU-Patch: Towards Efficient Instance Segmentation for Unseen Objects in Auto-Store0
Video Instance MattingCode1
Zero-Shot Enhancement of Low-Light Image Based on Retinex DecompositionCode0
SegGen: Supercharging Segmentation Models with Text2Mask and Mask2Img Synthesis0
Show:102550
← PrevPage 23 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