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 651675 of 2262 papers

TitleStatusHype
EDAPS: Enhanced Domain-Adaptive Panoptic SegmentationCode1
Improving Convolutional Networks With Self-Calibrated ConvolutionsCode1
Quality-Aware Network for Human ParsingCode1
MViTv2: Improved Multiscale Vision Transformers for Classification and DetectionCode1
Effective Self-supervised Pre-training on Low-compute Networks without DistillationCode1
Active Pointly-Supervised Instance SegmentationCode1
Improving Video Instance Segmentation via Temporal Pyramid RoutingCode1
Efficient Connectivity-Preserving Instance Segmentation with Supervoxel-Based Loss FunctionCode1
Incremental Few-Shot Instance SegmentationCode1
Inception Convolution with Efficient Dilation SearchCode1
EPSANet: An Efficient Pyramid Squeeze Attention Block on Convolutional Neural NetworkCode1
OoDIS: Anomaly Instance Segmentation BenchmarkCode1
UVO Challenge on Video-based Open-World Segmentation 2021: 1st Place SolutionCode1
EfficientPS: Efficient Panoptic SegmentationCode1
Open-Vocabulary Instance Segmentation via Robust Cross-Modal Pseudo-LabelingCode1
Efficient Self-supervised Vision Pretraining with Local Masked ReconstructionCode1
End-to-End Referring Video Object Segmentation with Multimodal TransformersCode1
Instance As Identity: A Generic Online Paradigm for Video Instance SegmentationCode1
Instance Brownian Bridge as Texts for Open-vocabulary Video Instance SegmentationCode1
Balanced Meta-Softmax for Long-Tailed Visual RecognitionCode1
End-to-End Semi-Supervised Object Detection with Soft TeacherCode1
All in Tokens: Unifying Output Space of Visual Tasks via Soft TokenCode1
Instance Segmentation in 3D Scenes using Semantic Superpoint Tree NetworksCode1
Improving Weakly-supervised Video Instance Segmentation by Leveraging Spatio-temporal ConsistencyCode1
OGC: Unsupervised 3D Object Segmentation from Rigid Dynamics of Point CloudsCode1
Show:102550
← PrevPage 27 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