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 12511275 of 2262 papers

TitleStatusHype
gSwin: Gated MLP Vision Model with Hierarchical Structure of Shifted Window0
Guided Table Structure Recognition through Anchor Optimization0
HAISTA-NET: Human Assisted Instance Segmentation Through Attention0
H-EMD: A Hierarchical Earth Mover's Distance Method for Instance Segmentation0
HIDA: Towards Holistic Indoor Understanding for the Visually Impaired via Semantic Instance Segmentation with a Wearable Solid-State LiDAR Sensor0
Hierarchical Lovász Embeddings for Proposal-free Panoptic Segmentation0
Hierarchical Lovasz Embeddings for Proposal-Free Panoptic Segmentation0
UniDAformer: Unified Domain Adaptive Panoptic Segmentation Transformer via Hierarchical Mask Calibration0
Hierarchical Side-Tuning for Vision Transformers0
High-throughput Phenotyping of Nematode Cysts0
HiRes-FusedMIM: A High-Resolution RGB-DSM Pre-trained Model for Building-Level Remote Sensing Applications0
HiT: Building Mapping with Hierarchical Transformers0
Holistic Understanding of 3D Scenes as Universal Scene Description0
HoughCL: Finding Better Positive Pairs in Dense Self-supervised Learning0
How can we learn (more) from challenges? A statistical approach to driving future algorithm development0
How do Cross-View and Cross-Modal Alignment Affect Representations in Contrastive Learning?0
How Object Information Improves Skeleton-based Human Action Recognition in Assembly Tasks0
HR-RCNN: Hierarchical Relational Reasoning for Object Detection0
hSDB-instrument: Instrument Localization Database for Laparoscopic and Robotic Surgeries0
Human Body Shape Classification Based on a Single Image0
Human De-occlusion: Invisible Perception and Recovery for Humans0
Human Extraction and Scene Transition utilizing Mask R-CNN0
Human Instance Segmentation and Tracking via Data Association and Single-stage Detector0
HUNIS: High-Performance Unsupervised Nuclei Instance Segmentation0
Hyb-KAN ViT: Hybrid Kolmogorov-Arnold Networks Augmented Vision Transformer0
Show:102550
← PrevPage 51 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