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 526550 of 2262 papers

TitleStatusHype
FinnWoodlands DatasetCode1
Fine-Grained Vehicle Perception via 3D Part-Guided Visual Data AugmentationCode1
FipTR: A Simple yet Effective Transformer Framework for Future Instance Prediction in Autonomous DrivingCode1
Evaluation of Segment Anything Model 2: The Role of SAM2 in the Underwater EnvironmentCode1
Benchmarking Self-Supervised Learning on Diverse Pathology DatasetsCode1
FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular CamerasCode1
FcaNet: Frequency Channel Attention NetworksCode1
Faster Mean-shift: GPU-accelerated clustering for cosine embedding-based cell segmentation and trackingCode1
Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayersCode1
Fashionpedia: Ontology, Segmentation, and an Attribute Localization DatasetCode1
Deep Variational Instance SegmentationCode1
BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask LearningCode1
FAPIS: A Few-shot Anchor-free Part-based Instance SegmenterCode1
Fast and Efficient Transformer-based Method for Bird's Eye View Instance PredictionCode1
Focal Self-attention for Local-Global Interactions in Vision TransformersCode1
Deep-learning in the bioimaging wild: Handling ambiguous data with deepflash2Code1
BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance SegmentationCode1
Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene ContextsCode1
Explain Any Concept: Segment Anything Meets Concept-Based ExplanationCode1
3D Indoor Instance Segmentation in an Open-WorldCode1
FASA: Feature Augmentation and Sampling Adaptation for Long-Tailed Instance SegmentationCode1
Expediting Large-Scale Vision Transformer for Dense Prediction without Fine-tuningCode1
Exploring Classification Equilibrium in Long-Tailed Object DetectionCode1
Evaluation Study on SAM 2 for Class-agnostic Instance-level SegmentationCode1
Deep Learning based Food Instance Segmentation using Synthetic DataCode1
Show:102550
← PrevPage 22 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