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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 251–300 of 2262 papers

TitleStatusHype
Improving Weakly-supervised Video Instance Segmentation by Leveraging Spatio-temporal ConsistencyCode1
InstanSeg: an embedding-based instance segmentation algorithm optimized for accurate, efficient and portable cell segmentationCode3
DQFormer: Towards Unified LiDAR Panoptic Segmentation with Decoupled Queries—0
Knowledge Discovery in Optical Music Recognition: Enhancing Information Retrieval with Instance Segmentation—0
A Survey of Camouflaged Object Detection and BeyondCode3
Satellite Sunroof: High-res Digital Surface Models and Roof Segmentation for Global Solar Mapping—0
A Brief Analysis of the Iterative Next Boundary Detection Network for Tree Rings Delineation in Images of Pinus taedaCode0
Image Segmentation in Foundation Model Era: A SurveyCode2
Symmetric masking strategy enhances the performance of Masked Image Modeling—0
ISETHDR: A Physics-based Synthetic Radiance Dataset for High Dynamic Range Driving ScenesCode1
EmbodiedSAM: Online Segment Any 3D Thing in Real TimeCode4
Open-Ended 3D Point Cloud Instance Segmentation—0
NuSegDG: Integration of Heterogeneous Space and Gaussian Kernel for Domain-Generalized Nuclei SegmentationCode1
An Interpretable Deep Learning Approach for Morphological Script Type Analysis—0
LSVOS Challenge 3rd Place Report: SAM2 and Cutie based VOS—0
Vocabulary-Free 3D Instance Segmentation with Vision and Language Assistant—0
Leveraging Superfluous Information in Contrastive Representation Learning—0
3D-Aware Instance Segmentation and Tracking in Egocentric Videos—0
GoodSAM++: Bridging Domain and Capacity Gaps via Segment Anything Model for Panoramic Semantic Segmentation—0
Tell Codec What Worth Compressing: Semantically Disentangled Image Coding for Machine with LMMs—0
Zero-Shot Dual-Path Integration Framework for Open-Vocabulary 3D Instance Segmentation—0
Tuning a SAM-Based Model with Multi-Cognitive Visual Adapter to Remote Sensing Instance Segmentation—0
5%>100%: Breaking Performance Shackles of Full Fine-Tuning on Visual Recognition TasksCode3
Performance Evaluation of YOLOv8 Model Configurations, for Instance Segmentation of Strawberry Fruit Development Stages in an Open Field Environment—0
Assessment of Cell Nuclei AI Foundation Models in Kidney PathologyCode0
Robust Approximate Characterization of Single-Cell Heterogeneity in Microbial GrowthCode0
Embodied Uncertainty-Aware Object Segmentation—0
Path-SAM2: Transfer SAM2 for digital pathology semantic segmentationCode1
CAS-ViT: Convolutional Additive Self-attention Vision Transformers for Efficient Mobile ApplicationsCode2
Evaluation of Segment Anything Model 2: The Role of SAM2 in the Underwater EnvironmentCode1
NuLite -- Lightweight and Fast Model for Nuclei Instance Segmentation and ClassificationCode1
Amodal Segmentation for Laparoscopic Surgery Video Instruments—0
A Simple Background Augmentation Method for Object Detection with Diffusion Model—0
MaskUno: Switch-Split Block For Enhancing Instance Segmentation—0
Depth-Wise Convolutions in Vision Transformers for Efficient Training on Small DatasetsCode1
A Survey on Cell Nuclei Instance Segmentation and Classification: Leveraging Context and Attention—0
LKCell: Efficient Cell Nuclei Instance Segmentation with Large Convolution KernelsCode1
McGAN: Generating Manufacturable Designs by Embedding Manufacturing Rules into Conditional Generative Adversarial Network—0
PartGLEE: A Foundation Model for Recognizing and Parsing Any ObjectsCode2
Enhancing Cell Instance Segmentation in Scanning Electron Microscopy Images via a Deep Contour Closing Operator—0
Panoptic Segmentation of Mammograms with Text-To-Image Diffusion Model—0
Scale Disparity of Instances in Interactive Point Cloud Segmentation—0
GroupMamba: Efficient Group-Based Visual State Space ModelCode2
ColorMAE: Exploring data-independent masking strategies in Masked AutoEncodersCode0
AdaLog: Post-Training Quantization for Vision Transformers with Adaptive Logarithm QuantizerCode1
Close the Sim2real Gap via Physically-based Structured Light Synthetic Data Simulation—0
Serialized Point Mamba: A Serialized Point Cloud Mamba Segmentation Model—0
Generative AI Driven Task-Oriented Adaptive Semantic Communications—0
Crowd-SAM: SAM as a Smart Annotator for Object Detection in Crowded ScenesCode2
SGIFormer: Semantic-guided and Geometric-enhanced Interleaving Transformer for 3D Instance SegmentationCode1
Show:102550
← PrevPage 6 of 46Next →
All datasetsCOCO test-devCOCO minivalLVIS v1.0 valCityscapes valADE20K valARMBenchOccluded COCOOoDISSeparated COCOTBBRBDD100K valCOCO val (panoptic labels)

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1InternImage-HAP5080.8—Unverified
2ResNeSt-200 (multi-scale)AP5070.2—Unverified
3CenterMask + VoVNetV2-99 (multi-scale)AP5066.2—Unverified
4CenterMask + VoVNetV2-57 (single-scale)AP5060.8—Unverified
5Co-DETRmask AP57.1—Unverified
6CBNetV2 (EVA02, single-scale)mask AP56.1—Unverified
7ISDA (ResNet-50)APL55.7—Unverified
8EVAmask AP55.5—Unverified
9FD-SwinV2-Gmask AP55.4—Unverified
10Mask Frozen-DETRmask AP55.3—Unverified
#ModelMetricClaimedVerifiedStatus
1InternImage-BGFLOPs501—Unverified
2Co-DETRmask AP56.6—Unverified
3ViT-CoMer-L (Mask RCNN, DINOv2)mask AP55.9—Unverified
4InternImage-Hmask AP55.4—Unverified
5EVAmask AP55—Unverified
6Mask Frozen-DETRmask AP54.9—Unverified
7MasK DINO (SwinL, multi-scale)mask AP54.5—Unverified
8GLEE-Promask AP54.2—Unverified
9ViT-Adapter-L (HTC++, BEiTv2, O365, multi-scale)mask AP54.2—Unverified
10SwinV2-G (HTC++)mask AP53.7—Unverified