Computer Code
 
Edit

Semantic Segmentation

5248 papers with code • 125 benchmarks • 312 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
8,282
rwightman/pytorch-image-models
33 papers
29,908
osmr/imgclsmob
30 papers
2,924
open-mmlab/mmsegmentation
19 papers
7,454
See all 39 libraries.

Datasets

Subtasks

GLIMS: Attention-Guided Lightweight Multi-Scale Hybrid Network for Volumetric Semantic Segmentation

yaziciz/GLIMS • 27 Apr 2024

Notably, GLIMS achieved this high performance with a significantly reduced number of trainable parameters.

1
27 Apr 2024
Paper
Code

Multi-Scale Representations by Varying Window Attention for Semantic Segmentation

yan-hao-tian/lawin • • 25 Apr 2024

VWA leverages the local window attention (LWA) and disentangles LWA into the query window and context window, allowing the context's scale to vary for the query to learn representations at multiple scales.

110
25 Apr 2024
Paper
Code

A Multi-objective Optimization Benchmark Test Suite for Real-time Semantic Segmentation

emi-group/evoxbench • • 25 Apr 2024

To bridge the gap, we introduce a tailored streamline to transform the task of HW-NAS for real-time semantic segmentation into standard MOPs.

73
25 Apr 2024
Paper
Code

Multimodal Information Interaction for Medical Image Segmentation

fxxjuses/micformer • • 25 Apr 2024

To address this issue, we introduce an innovative Multimodal Information Cross Transformer (MicFormer), which employs a dual-stream architecture to simultaneously extract features from each modality.

8
25 Apr 2024
Paper
Code

Boosting Unsupervised Semantic Segmentation with Principal Mask Proposals

visinf/primaps • • 25 Apr 2024

Unsupervised semantic segmentation aims to automatically partition images into semantically meaningful regions by identifying global categories within an image corpus without any form of annotation.

7
25 Apr 2024
Paper
Code

Self-Balanced R-CNN for Instance Segmentation

IMPLabUniPr/mmdetection • • 25 Apr 2024

Current state-of-the-art two-stage models on instance segmentation task suffer from several types of imbalances.

4
25 Apr 2024
Paper
Code

Auto-Generating Weak Labels for Real & Synthetic Data to Improve Label-Scarce Medical Image Segmentation

stanfordmlgroup/auto-generate-wls • • 25 Apr 2024

The high cost of creating pixel-by-pixel gold-standard labels, limited expert availability, and presence of diverse tasks make it challenging to generate segmentation labels to train deep learning models for medical imaging tasks.

4
25 Apr 2024
Paper
Code

OMEGAS: Object Mesh Extraction from Large Scenes Guided by Gaussian Segmentation

crystalwlz/omegas • • 24 Apr 2024

Current scene reconstruction techniques frequently result in the loss of object detail textures and are unable to reconstruct object portions that are occluded or unseen in views.

23
24 Apr 2024
Paper
Code

Vision Transformer-based Adversarial Domain Adaptation

lluckyyh/vt-ada • • 24 Apr 2024

Unsupervised domain adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain.

3
24 Apr 2024
Paper
Code

Surgical-DeSAM: Decoupling SAM for Instrument Segmentation in Robotic Surgery

yuyangsheng/surgical-desam • • 22 Apr 2024

We utilise a commonly used detection architecture, DETR, and fine-tuned it to obtain bounding box prompt for the instruments.

1
22 Apr 2024
Paper
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