Interactive Segmentation
50 papers with code • 12 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
COCO
Cityscapes
DAVIS
PASCAL VOC
SBD
ssTEM
DAVIS-585
Most implemented papers
Reviving Iterative Training with Mask Guidance for Interactive Segmentation
saic-vul/ritm_interactive_segmentation
•
•
We find that the models trained on a combination of COCO and LVIS with diverse and high-quality annotations show performance superior to all existing models.
Deep Interactive Object Selection
Interactive object selection is a very important research problem and has many applications.
f-BRS: Rethinking Backpropagating Refinement for Interactive Segmentation
saic-vul/fbrs_interactive_segmentation
•
•
CVPR 2020
We propose f-BRS (feature backpropagating refinement scheme) that solves an optimization problem with respect to auxiliary variables instead of the network inputs, and requires running forward and backward pass just for a small part of a network.
Getting to 99% Accuracy in Interactive Segmentation
We propose a novel interactive architecture and a novel training scheme that are both tailored to better exploit the user workflow.
NuClick: A Deep Learning Framework for Interactive Segmentation of Microscopy Images
As nuclei, cells and glands are fundamental objects for downstream analysis in computational pathology/cytology, in this paper we propose a simple CNN-based approach to speed up collecting annotations for these objects which requires minimum interaction from the annotator.
EdgeFlow: Achieving Practical Interactive Segmentation with Edge-Guided Flow
In addition, with the proposed method, we develop an efficient interactive segmentation tool for practical data annotation tasks.
Segment Everything Everywhere All at Once
ux-decoder/segment-everything-everywhere-all-at-once
•
•
In SEEM, we propose a novel decoding mechanism that enables diverse prompting for all types of segmentation tasks, aiming at a universal segmentation interface that behaves like large language models (LLMs).
SAM-Med2D
To bridge this gap, we introduce SAM-Med2D, the most comprehensive studies on applying SAM to medical 2D images.
Deep Extreme Cut: From Extreme Points to Object Segmentation
scaelles/DEXTR-PyTorch
•
•
CVPR 2018
This paper explores the use of extreme points in an object (left-most, right-most, top, bottom pixels) as input to obtain precise object segmentation for images and videos.
Interactive Object Segmentation With Inside-Outside Guidance
shiyinzhang/Inside-Outside-Guidance
•
•
CVPR 2020
This paper explores how to harvest precise object segmentation masks while minimizing the human interaction cost.
