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 451475 of 2262 papers

TitleStatusHype
Eigencontours: Novel Contour Descriptors Based on Low-Rank ApproximationCode1
Affinity Attention Graph Neural Network for Weakly Supervised Semantic SegmentationCode1
BlockCopy: High-Resolution Video Processing with Block-Sparse Feature Propagation and Online PoliciesCode1
Contextual Transformer Networks for Visual RecognitionCode1
BlendMask: Top-Down Meets Bottom-Up for Instance SegmentationCode1
MutualNet: Adaptive ConvNet via Mutual Learning from Network Width and ResolutionCode1
Cross-Layer Retrospective Retrieving via Layer AttentionCode1
ContourFormer:Real-Time Contour-Based End-to-End Instance Segmentation TransformerCode1
AugmenTory: A Fast and Flexible Polygon Augmentation LibraryCode1
Contour Proposal Networks for Biomedical Instance SegmentationCode1
Efficient Self-supervised Vision Pretraining with Local Masked ReconstructionCode1
EM-Paste: EM-guided Cut-Paste with DALL-E Augmentation for Image-level Weakly Supervised Instance SegmentationCode1
Efficient Connectivity-Preserving Instance Segmentation with Supervoxel-Based Loss FunctionCode1
Contrastive Lift: 3D Object Instance Segmentation by Slow-Fast Contrastive FusionCode1
Contrastive Object-level Pre-training with Spatial Noise Curriculum LearningCode1
ContrastMask: Contrastive Learning to Segment Every ThingCode1
ConvMLP: Hierarchical Convolutional MLPs for VisionCode1
AggMask: Exploring locally aggregated learning of mask representations for instance segmentationCode1
MEDIAR: Harmony of Data-Centric and Model-Centric for Multi-Modality MicroscopyCode1
Med-Query: Steerable Parsing of 9-DoF Medical Anatomies with Query EmbeddingCode1
AutoFocusFormer: Image Segmentation off the GridCode1
Co-Scale Conv-Attentional Image TransformersCode1
AutoInst: Automatic Instance-Based Segmentation of LiDAR 3D ScansCode1
Effective Self-supervised Pre-training on Low-compute Networks without DistillationCode1
A Close Look at Spatial Modeling: From Attention to ConvolutionCode1
Show:102550
← PrevPage 19 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