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 21512175 of 2262 papers

TitleStatusHype
The Second Place Solution for ICCV2021 VIPriors Instance Segmentation Challenge0
The Semantic Mutex Watershed for Efficient Bottom-Up Semantic Instance Segmentation0
Four Ways to Improve Verbo-visual Fusion for Dense 3D Visual Grounding0
Time-Space Transformers for Video Panoptic Segmentation0
Tomato Multi-Angle Multi-Pose Dataset for Fine-Grained Phenotyping0
Tooth Instance Segmentation from Cone-Beam CT Images through Point-based Detection and Gaussian Disentanglement0
ToothNet: Automatic Tooth Instance Segmentation and Identification From Cone Beam CT Images0
torchdistill: A Modular, Configuration-Driven Framework for Knowledge Distillation0
TorontoCity: Seeing the World with a Million Eyes0
ToSkA: Topological Skeleton Analysis for Network-Based Shape Representation and Evaluation of Objects from Cells to Death Stars0
Toward Joint Thing-and-Stuff Mining for Weakly Supervised Panoptic Segmentation0
ASIST: Annotation-free Synthetic Instance Segmentation and Tracking by Adversarial Simulations0
Towards Autonomous Driving: a Multi-Modal 360^ Perception Proposal0
Towards Bounding-Box Free Panoptic Segmentation0
Towards general deep-learning-based tree instance segmentation models0
Towards Good Practices for Instance Segmentation0
Towards Instance Segmentation with Object Priority: Prominent Object Detection and Recognition0
Towards Panoptic 3D Parsing for Single Image in the Wild0
Towards Robust Part-aware Instance Segmentation for Industrial Bin Picking0
Towards Robust Video Instance Segmentation with Temporal-Aware Transformer0
Towards Unconstrained End-to-End Text Spotting0
Towards Universal Vision-language Omni-supervised Segmentation0
TraceNet: Segment one thing efficiently0
TrafficCAM: A Versatile Dataset for Traffic Flow Segmentation0
Training-Free Open-Ended Object Detection and Segmentation via Attention as Prompts0
Show:102550
← PrevPage 87 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