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 15011525 of 2262 papers

TitleStatusHype
Object as Distribution0
Object Detection Free Instance Segmentation With Labeling Transformations0
Object-Guided Instance Segmentation for Biological Images0
ObjectMix: Data Augmentation by Copy-Pasting Objects in Videos for Action Recognition0
Object segmentation in depth maps with one user click and a synthetically trained fully convolutional network0
Object Segmentation with Audio Context0
Occluded Video Instance Segmentation: Dataset and ICCV 2021 Challenge0
Occlusion-Ordered Semantic Instance Segmentation0
Occlusion Reasoning for Skeleton Extraction of Self-Occluded Tree Canopies0
Occlusion-Resistant Instance Segmentation of Piglets in Farrowing Pens Using Center Clustering Network0
OccuSeg: Occupancy-aware 3D Instance Segmentation0
Offline-to-Online Knowledge Distillation for Video Instance Segmentation0
Offshore Wind Plant Instance Segmentation Using Sentinel-1 Time Series, GIS, and Semantic Segmentation Models0
OG: Equip vision occupancy with instance segmentation and visual grounding0
OmniCity: Omnipotent City Understanding with Multi-level and Multi-view Images0
On Domain-Specific Pre-Training for Effective Semantic Perception in Agricultural Robotics0
On generalisability of segment anything model for nuclear instance segmentation in histology images0
OnlineAnySeg: Online Zero-Shot 3D Segmentation by Visual Foundation Model Guided 2D Mask Merging0
Online Video Instance Segmentation via Robust Context Fusion0
On Mutual Information in Contrastive Learning for Visual Representations0
On Steering Multi-Annotations per Sample for Multi-Task Learning0
On the Efficacy of Multi-scale Data Samplers for Vision Applications0
On the Importance of Visual Context for Data Augmentation in Scene Understanding0
OpenDAS: Open-Vocabulary Domain Adaptation for 2D and 3D Segmentation0
Open-Ended 3D Point Cloud Instance Segmentation0
Show:102550
← PrevPage 61 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