SOTAVerified

Semantic Segmentation

Papers

Showing 10511100 of 14763 papers

TitleStatusHype
Activation Modulation and Recalibration Scheme for Weakly Supervised Semantic SegmentationCode1
CalibNet: Dual-branch Cross-modal Calibration for RGB-D Salient Instance SegmentationCode1
A Learning Strategy for Contrast-agnostic MRI SegmentationCode1
Evaluation of Segment Anything Model 2: The Role of SAM2 in the Underwater EnvironmentCode1
Cached Transformers: Improving Transformers with Differentiable Memory CacheCode1
Depth-aware Object Segmentation and Grasp Detection for Robotic Picking TasksCode1
Depthformer : Multiscale Vision Transformer For Monocular Depth Estimation With Local Global Information FusionCode1
Detect Any Shadow: Segment Anything for Video Shadow DetectionCode1
DSU-Net:An Improved U-Net Model Based on DINOv2 and SAM2 with Multi-scale Cross-model Feature EnhancementCode1
Diffusion Models for Implicit Image Segmentation EnsemblesCode1
Activate or Not: Learning Customized ActivationCode1
BURST: A Benchmark for Unifying Object Recognition, Segmentation and Tracking in VideoCode1
DenseHybrid: Hybrid Anomaly Detection for Dense Open-set RecognitionCode1
DensePASS: Dense Panoramic Semantic Segmentation via Unsupervised Domain Adaptation with Attention-Augmented Context ExchangeCode1
A Large-Scale Network Construction and Lightweighting Method for Point Cloud Semantic SegmentationCode1
ActionVOS: Actions as Prompts for Video Object SegmentationCode1
Building Extraction from Remote Sensing Images via an Uncertainty-Aware NetworkCode1
A Large-Scale Benchmark for Food Image SegmentationCode1
ACTION++: Improving Semi-supervised Medical Image Segmentation with Adaptive Anatomical ContrastCode1
BuildingNet: Learning to Label 3D BuildingsCode1
Dense Siamese Network for Dense Unsupervised LearningCode1
DenseCLIP: Language-Guided Dense Prediction with Context-Aware PromptingCode1
Dense Contrastive Learning for Self-Supervised Visual Pre-TrainingCode1
BT-Unet: A self-supervised learning framework for biomedical image segmentation using Barlow Twins with U-Net modelsCode1
Extract Free Dense Labels from CLIPCode1
Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot SegmentationCode1
On the Connection between Local Attention and Dynamic Depth-wise ConvolutionCode1
BSNet: Box-Supervised Simulation-assisted Mean Teacher for 3D Instance SegmentationCode1
DenoiseRep: Denoising Model for Representation LearningCode1
Building a Strong Pre-Training Baseline for Universal 3D Large-Scale PerceptionCode1
Bridging Vision and Language Encoders: Parameter-Efficient Tuning for Referring Image SegmentationCode1
Delving into the Cyclic Mechanism in Semi-supervised Video Object SegmentationCode1
Latent Diffusion for Medical Image Segmentation: End to end learning for fast sampling and accuracyCode1
Dense Dilated Convolutions Merging Network for Land Cover ClassificationCode1
Dense Unsupervised Learning for Video SegmentationCode1
DeltaConv: Anisotropic Operators for Geometric Deep Learning on Point CloudsCode1
Bridge the Points: Graph-based Few-shot Segment Anything SemanticallyCode1
Delving Deeper into Anti-aliasing in ConvNetsCode1
AISFormer: Amodal Instance Segmentation with TransformerCode1
1st Place Solution for 5th LSVOS Challenge: Referring Video Object SegmentationCode1
Delving Deep Into Many-to-Many Attention for Few-Shot Video Object SegmentationCode1
Breaking Shortcut: Exploring Fully Convolutional Cycle-Consistency for Video Correspondence LearningCode1
AI-SAM: Automatic and Interactive Segment Anything ModelCode1
3D Part Guided Image Editing for Fine-Grained Object UnderstandingCode1
Bridging the Domain Gap: Self-Supervised 3D Scene Understanding with Foundation ModelsCode1
Delving into Crispness: Guided Label Refinement for Crisp Edge DetectionCode1
BPKD: Boundary Privileged Knowledge Distillation For Semantic SegmentationCode1
DeformUX-Net: Exploring a 3D Foundation Backbone for Medical Image Segmentation with Depthwise Deformable ConvolutionCode1
DeiSAM: Segment Anything with Deictic PromptingCode1
AI Playground: Unreal Engine-based Data Ablation Tool for Deep LearningCode1
Show:102550
← PrevPage 22 of 296Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1InternImage-H (M3I Pre-training)Params (M)1,310Unverified
2ViT-P (InternImage-H)Validation mIoU63.6Unverified
3ONE-PEACEValidation mIoU63Unverified
4InternImage-HValidation mIoU62.9Unverified
5M3I Pre-training (InternImage-H)Validation mIoU62.9Unverified
6BEiT-3Validation mIoU62.8Unverified
7EVAValidation mIoU62.3Unverified
8ViT-P (OneFormer, InternImage-H)Validation mIoU61.6Unverified
9ViT-Adapter-L (Mask2Former, BEiTv2 pretrain)Validation mIoU61.5Unverified
10FD-SwinV2-GValidation mIoU61.4Unverified