Interactive Segmentation
65 papers with code • 14 benchmarks • 8 datasets
Benchmarks
These leaderboards are used to track progress in Interactive Segmentation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Interactive Segmentation models and implementations
MS COCO
Cityscapes
DAVIS
PASCAL VOC
SBD
ssTEM
DAVIS-585
Latest papers
PRISM: A Promptable and Robust Interactive Segmentation Model with Visual Prompts
medicl-vu/prism
•
•
(3) Corrective learning.
Rethinking Interactive Image Segmentation with Low Latency, High Quality, and Diverse Prompts
uncbiag/segnext
•
•
In light of this, we reintroduce this dense design into the generalist models, to facilitate the development of generalist models with high segmentation quality.
Clustering Propagation for Universal Medical Image Segmentation
}$ This enables knowledge acquired from prior slices to assist in the segmentation of the current slice, further efficiently bridging the communication between remote slices using mere 2D networks.
Leveraging AI Predicted and Expert Revised Annotations in Interactive Segmentation: Continual Tuning or Full Training?
Human experts revise the annotations predicted by AI, and in turn, AI improves its predictions by learning from these revised annotations.
OMG-Seg: Is One Model Good Enough For All Segmentation?
lxtgh/omg-seg
•
•
In this work, we address various segmentation tasks, each traditionally tackled by distinct or partially unified models.
RAP-SAM: Towards Real-Time All-Purpose Segment Anything
Segment Anything Model (SAM) is one remarkable model that can achieve generalized segmentation.
A Simple Latent Diffusion Approach for Panoptic Segmentation and Mask Inpainting
segments-ai/latent-diffusion-segmentation
•
•
Panoptic and instance segmentation networks are often trained with specialized object detection modules, complex loss functions, and ad-hoc post-processing steps to handle the permutation-invariance of the instance masks.
MST: Adaptive Multi-Scale Tokens Guided Interactive Segmentation
To address the target scale variation issue in interactive segmentation, a novel multi-scale token adaptation algorithm is proposed.
Open-Vocabulary SAM: Segment and Recognize Twenty-thousand Classes Interactively
harboryuan/ovsam
•
•
The CLIP and Segment Anything Model (SAM) are remarkable vision foundation models (VFMs).
ScribblePrompt: Fast and Flexible Interactive Segmentation for Any Biomedical Image
These include a training strategy that incorporates both a highly diverse set of images and tasks, novel algorithms for simulated user interactions and labels, and a network that enables fast inference.
