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 12011225 of 2262 papers

TitleStatusHype
3rd Place Solution for PVUW Challenge 2023: Video Panoptic Segmentation0
4DContrast: Contrastive Learning with Dynamic Correspondences for 3D Scene Understanding0
A2D2: Audi Autonomous Driving Dataset0
A^2-FPN: Attention Aggregation based Feature Pyramid Network for Instance Segmentation0
A2-FPN: Attention Aggregation Based Feature Pyramid Network for Instance Segmentation0
A2VIS: Amodal-Aware Approach to Video Instance Segmentation0
A Benchmark for LiDAR-based Panoptic Segmentation based on KITTI0
A Bilayer Segmentation-Recombination Network for Accurate Segmentation of Overlapping C. elegans0
Abnormal activity capture from passenger flow of elevator based on unsupervised learning and fine-grained multi-label recognition0
Investigating Object Compositionality in Generative Adversarial Networks0
Accelerating the creation of instance segmentation training sets through bounding box annotation0
Accurate and efficient zero-shot 6D pose estimation with frozen foundation models0
Accurately identifying vertebral levels in large datasets0
ACDC: The Adverse Conditions Dataset with Correspondences for Robust Semantic Driving Scene Perception0
A Closed-Loop System for Improving Annotation Quality and Efficiency0
A closer look at network resolution for efficient network design0
A Coarse-to-Fine Instance Segmentation Network with Learning Boundary Representation0
A Comprehensive Survey on Video Scene Parsing:Advances, Challenges, and Prospects0
A Convolutional Neural Network for Point Cloud Instance Segmentation in Cluttered Scene Trained by Synthetic Data Without Color0
Acquire, Augment, Segment & Enjoy: Weakly Supervised Instance Segmentation of Supermarket Products0
Active Testing: An Efficient and Robust Framework for Estimating Accuracy0
Actor-Action Semantic Segmentation with Region Masks0
AdaMV-MoE: Adaptive Multi-Task Vision Mixture-of-Experts0
Adapting Mask-RCNN for Automatic Nucleus Segmentation0
Adapting SAM for Volumetric X-Ray Data-sets of Arbitrary Sizes0
Show:102550
← PrevPage 49 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