Image Segmentation
1508 papers with code • 3 benchmarks • 20 datasets
Image Segmentation is a computer vision task that involves dividing an image into multiple segments or regions, each of which corresponds to a different object or part of an object. The goal of image segmentation is to assign a unique label or category to each pixel in the image, so that pixels with similar attributes are grouped together.
Benchmarks
These leaderboards are used to track progress in Image Segmentation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
Libraries
Use these libraries to find Image Segmentation models and implementationsDatasets
SA-1B
MCubeS
Pascal Panoptic Parts
MARIDA
EntitySeg
HuTu 80
Raw-Microscopy and Raw-Drone
Pothole Mix
TomoSAM
Most implemented papers
W-Net: A Deep Model for Fully Unsupervised Image Segmentation
While significant attention has been recently focused on designing supervised deep semantic segmentation algorithms for vision tasks, there are many domains in which sufficient supervised pixel-level labels are difficult to obtain.
Concurrent Spatial and Channel Squeeze & Excitation in Fully Convolutional Networks
abhi4ssj/squeeze_and_excitation
•
•
Fully convolutional neural networks (F-CNNs) have set the state-of-the-art in image segmentation for a plethora of applications.
UNETR: Transformers for 3D Medical Image Segmentation
Project-MONAI/research-contributions
•
•
Inspired by the recent success of transformers for Natural Language Processing (NLP) in long-range sequence learning, we reformulate the task of volumetric (3D) medical image segmentation as a sequence-to-sequence prediction problem.
Panoptic Segmentation
We propose and study a task we name panoptic segmentation (PS).
nnU-Net: Self-adapting Framework for U-Net-Based Medical Image Segmentation
MIC-DKFZ/nnunet
•
•
The U-Net was presented in 2015.
Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation
idea-research/maskdino
•
•
CVPR 2023
In this paper we present Mask DINO, a unified object detection and segmentation framework.
Deep clustering: Discriminative embeddings for segmentation and separation
The framework can be used without class labels, and therefore has the potential to be trained on a diverse set of sound types, and to generalize to novel sources.
CompNet: Complementary Segmentation Network for Brain MRI Extraction
raun1/Complementary_Segmentation_Network
•
•
Brain extraction is a fundamental step for most brain imaging studies.
Uncertainty-aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentation
yulequan/UA-MT
•
•
We design a novel uncertainty-aware scheme to enable the student model to gradually learn from the meaningful and reliable targets by exploiting the uncertainty information.
One-Shot Learning for Semantic Segmentation
Low-shot learning methods for image classification support learning from sparse data.
