Computer Code
 
Edit

Semantic Segmentation

5232 papers with code • 125 benchmarks • 311 datasets

Semantic Segmentation is a computer vision task in which the goal is to categorize each pixel in an image into a class or object. The goal is to produce a dense pixel-wise segmentation map of an image, where each pixel is assigned to a specific class or object. Some example benchmarks for this task are Cityscapes, PASCAL VOC and ADE20K. Models are usually evaluated with the Mean Intersection-Over-Union (Mean IoU) and Pixel Accuracy metrics.

( Image credit: CSAILVision )

Libraries

Use these libraries to find Semantic Segmentation models and implementations
PaddlePaddle/PaddleSeg
53 papers
8,269
rwightman/pytorch-image-models
33 papers
29,867
osmr/imgclsmob
30 papers
2,919
open-mmlab/mmsegmentation
19 papers
7,436
See all 39 libraries.

Datasets

Subtasks

Latest papers with no code

Most implemented Social Latest No code

IPixMatch: Boost Semi-supervised Semantic Segmentation with Inter-Pixel Relation

no code yet • 29 Apr 2024

The scarcity of labeled data in real-world scenarios is a critical bottleneck of deep learning's effectiveness.

 
Paper
Add Code

U-Nets as Belief Propagation: Efficient Classification, Denoising, and Diffusion in Generative Hierarchical Models

no code yet • 29 Apr 2024

U-Nets are among the most widely used architectures in computer vision, renowned for their exceptional performance in applications such as image segmentation, denoising, and diffusion modeling.

 
Paper
Add Code

Swin2-MoSE: A New Single Image Super-Resolution Model for Remote Sensing

no code yet • 29 Apr 2024

Due to the limitations of current optical and sensor technologies and the high cost of updating them, the spectral and spatial resolution of satellites may not always meet desired requirements.

 
Paper
Add Code

Clicks2Line: Using Lines for Interactive Image Segmentation

no code yet • 29 Apr 2024

To reduce the amount of user-effort required, we propose using lines instead of clicks for such cases.

 
Paper
Add Code

MFP: Making Full Use of Probability Maps for Interactive Image Segmentation

no code yet • 29 Apr 2024

In recent interactive segmentation algorithms, previous probability maps are used as network input to help predictions in the current segmentation round.

 
Paper
Add Code

Open-Set 3D Semantic Instance Maps for Vision Language Navigation -- O3D-SIM

no code yet • 27 Apr 2024

Humans excel at forming mental maps of their surroundings, equipping them to understand object relationships and navigate based on language queries.

 
Paper
Add Code

Segmentation Quality and Volumetric Accuracy in Medical Imaging

no code yet • 27 Apr 2024

Current medical image segmentation relies on the region-based (Dice, F1-score) and boundary-based (Hausdorff distance, surface distance) metrics as the de-facto standard.

 
Paper
Add Code

Optimizing Universal Lesion Segmentation: State Space Model-Guided Hierarchical Networks with Feature Importance Adjustment

no code yet • 26 Apr 2024

Deep learning has revolutionized medical imaging by providing innovative solutions to complex healthcare challenges.

 
Paper
Add Code

DiffSeg: A Segmentation Model for Skin Lesions Based on Diffusion Difference

no code yet • 25 Apr 2024

However, the accuracy of the segmentation results is often limited by insufficient supervision and the complex nature of medical imaging.

 
Paper
Add Code

Semantic Segmentation Refiner for Ultrasound Applications with Zero-Shot Foundation Models

no code yet • 25 Apr 2024

Despite the remarkable success of deep learning in medical imaging analysis, medical image segmentation remains challenging due to the scarcity of high-quality labeled images for supervision.

 
Paper
Add Code
Contact us on: hello@paperswithcode.com . Papers With Code is a free resource with all data licensed under CC-BY-SA.
Terms Data policy Cookies policy