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 676700 of 2262 papers

TitleStatusHype
Deep Learning for Morphological Identification of Extended Radio Galaxies using Weak LabelsCode0
1st Place Solution for CVPR2023 BURST Long Tail and Open World Challenges0
Exploring Transformers for Open-world Instance Segmentation0
Mask Frozen-DETR: High Quality Instance Segmentation with One GPU0
Enhancing Nucleus Segmentation with HARU-Net: A Hybrid Attention Based Residual U-Blocks Network0
DiT: Efficient Vision Transformers with Dynamic Token RoutingCode0
FSD V2: Improving Fully Sparse 3D Object Detection with Virtual Voxels0
Syn-Mediverse: A Multimodal Synthetic Dataset for Intelligent Scene Understanding of Healthcare Facilities0
Guided Distillation for Semi-Supervised Instance SegmentationCode1
Weakly Supervised 3D Instance Segmentation without Instance-level Annotations0
LiDAR-Camera Panoptic Segmentation via Geometry-Consistent and Semantic-Aware AlignmentCode1
UGainS: Uncertainty Guided Anomaly Instance SegmentationCode1
NuInsSeg: A Fully Annotated Dataset for Nuclei Instance Segmentation in H&E-Stained Histological ImagesCode1
Synthetic Instance Segmentation from Semantic Image Segmentation MasksCode1
MonoNext: A 3D Monocular Object Detection with ConvNext0
Lowis3D: Language-Driven Open-World Instance-Level 3D Scene Understanding0
Unmasking Anomalies in Road-Scene SegmentationCode1
GaPro: Box-Supervised 3D Point Cloud Instance Segmentation Using Gaussian Processes as Pseudo LabelersCode1
CTVIS: Consistent Training for Online Video Instance SegmentationCode1
Learning Dynamic Query Combinations for Transformer-based Object Detection and SegmentationCode1
A novel integrated method of detection-grasping for specific object based on the box coordinate matching0
ClickSeg: 3D Instance Segmentation with Click-Level Weak Annotations0
Light-Weight Vision Transformer with Parallel Local and Global Self-Attention0
On Point Affiliation in Feature UpsamplingCode1
CalibNet: Dual-branch Cross-modal Calibration for RGB-D Salient Instance SegmentationCode1
Show:102550
← PrevPage 28 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