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 19511975 of 2262 papers

TitleStatusHype
A Novel Incremental Learning Driven Instance Segmentation Framework to Recognize Highly Cluttered Instances of the Contraband ItemsCode0
Geometry-Aware Instance Segmentation with Disparity MapsCode0
ClusterFuG: Clustering Fully connected Graphs by MulticutCode0
TCOVIS: Temporally Consistent Online Video Instance SegmentationCode0
Generator evaluator-selector net for panoptic image segmentation and splitting unfamiliar objects into partsCode0
UruDendro, a public dataset of cross-section images of Pinus taedaCode0
JSNet: Joint Instance and Semantic Segmentation of 3D Point CloudsCode0
Data Augmentation for Object Detection via Progressive and Selective Instance-SwitchingCode0
A Novel Deep Learning Approach Featuring Graph-Based Algorithm for Cell Segmentation and TrackingCode0
Generative Denoise Distillation: Simple Stochastic Noises Induce Efficient Knowledge Transfer for Dense PredictionCode0
Yeast cell segmentation in microstructured environments with deep learningCode0
CLIMB-3D: Continual Learning for Imbalanced 3D Instance SegmentationCode0
TensorMask: A Foundation for Dense Object SegmentationCode0
Tensor Pooling Driven Instance Segmentation Framework for Baggage Threat RecognitionCode0
TernausNetV2: Fully Convolutional Network for Instance SegmentationCode0
CircleSnake: Instance Segmentation with Circle RepresentationCode0
Circle Representation for Medical Instance Object SegmentationCode0
Gated Channel Transformation for Visual RecognitionCode0
Text and Click inputs for unambiguous open vocabulary instance segmentationCode0
CenterDisks: Real-time instance segmentation with disk coveringCode0
Recursively Refined R-CNN: Instance Segmentation with Self-RoI RebalancingCode0
Recurrent Pixel Embedding for Instance GroupingCode0
From Seedling to Harvest: The GrowingSoy Dataset for Weed Detection in Soy Crops via Instance SegmentationCode0
From Density to Geometry: YOLOv8 Instance Segmentation for Reverse Engineering of Optimized StructuresCode0
Recurrent Neural Networks for Semantic Instance SegmentationCode0
Show:102550
← PrevPage 79 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