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 101150 of 2262 papers

TitleStatusHype
GreedyViG: Dynamic Axial Graph Construction for Efficient Vision GNNsCode2
RelationField: Relate Anything in Radiance FieldsCode2
Revisiting Contrastive Methods for Unsupervised Learning of Visual RepresentationsCode2
RMT: Retentive Networks Meet Vision TransformersCode2
FusionVision: A comprehensive approach of 3D object reconstruction and segmentation from RGB-D cameras using YOLO and fast segment anythingCode2
Beyond Self-attention: External Attention using Two Linear Layers for Visual TasksCode2
Scene-Centric Unsupervised Panoptic SegmentationCode2
BlenderProcCode2
FreeSOLO: Learning to Segment Objects without AnnotationsCode2
Aerial Lifting: Neural Urban Semantic and Building Instance Lifting from Aerial ImageryCode2
GCNet: Non-local Networks Meet Squeeze-Excitation Networks and BeyondCode2
FastInst: A Simple Query-Based Model for Real-Time Instance SegmentationCode2
Contrastive Learning Rivals Masked Image Modeling in Fine-tuning via Feature DistillationCode2
Bottleneck Transformers for Visual RecognitionCode2
SPINEPS -- Automatic Whole Spine Segmentation of T2-weighted MR images using a Two-Phase Approach to Multi-class Semantic and Instance SegmentationCode2
Swin Transformer: Hierarchical Vision Transformer using Shifted WindowsCode2
The Missing Point in Vision Transformers for Universal Image SegmentationCode2
Box2Mask: Box-supervised Instance Segmentation via Level-set EvolutionCode2
Box-supervised Instance Segmentation with Level Set EvolutionCode2
Exploring Plain Vision Transformer Backbones for Object DetectionCode2
Unsupervised Universal Image SegmentationCode2
FEC: Fast Euclidean Clustering for Point Cloud SegmentationCode2
GroupMamba: Efficient Group-Based Visual State Space ModelCode2
MogaNet: Multi-order Gated Aggregation NetworkCode2
DreamColour: Controllable Video Colour Editing without TrainingCode2
VSA: Learning Varied-Size Window Attention in Vision TransformersCode2
ECA-Net: Efficient Channel Attention for Deep Convolutional Neural NetworksCode2
Diving into Underwater: Segment Anything Model Guided Underwater Salient Instance Segmentation and A Large-scale DatasetCode2
DiffusionInst: Diffusion Model for Instance SegmentationCode2
Dilated Neighborhood Attention TransformerCode2
Does Image Anonymization Impact Computer Vision Training?Code2
DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTsCode2
Delineate Anything: Resolution-Agnostic Field Boundary Delineation on Satellite ImageryCode2
CellViT: Vision Transformers for Precise Cell Segmentation and ClassificationCode2
Deep Snake for Real-Time Instance SegmentationCode2
DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous ConvolutionCode2
DI-MaskDINO: A Joint Object Detection and Instance Segmentation ModelCode2
DiverGen: Improving Instance Segmentation by Learning Wider Data Distribution with More Diverse Generative DataCode2
DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion ModelsCode2
E2EC: An End-to-End Contour-based Method for High-Quality High-Speed Instance SegmentationCode2
CAS-ViT: Convolutional Additive Self-attention Vision Transformers for Efficient Mobile ApplicationsCode2
ECLIPSE: Efficient Continual Learning in Panoptic Segmentation with Visual Prompt TuningCode2
DAT++: Spatially Dynamic Vision Transformer with Deformable AttentionCode2
Crowd-SAM: SAM as a Smart Annotator for Object Detection in Crowded ScenesCode2
DAMamba: Vision State Space Model with Dynamic Adaptive ScanCode2
A Simple Latent Diffusion Approach for Panoptic Segmentation and Mask InpaintingCode2
Fields of The World: A Machine Learning Benchmark Dataset For Global Agricultural Field Boundary SegmentationCode2
FM-Fusion: Instance-aware Semantic Mapping Boosted by Vision-Language Foundation ModelsCode2
Fully Convolutional Instance-aware Semantic SegmentationCode2
DaViT: Dual Attention Vision TransformersCode2
Show:102550
← PrevPage 3 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