Computer Code
 
Edit

Semantic Segmentation

5335 papers with code • 126 benchmarks • 317 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
8,347
rwightman/pytorch-image-models
33 papers
30,274
osmr/imgclsmob
30 papers
2,926
open-mmlab/mmsegmentation
19 papers
7,570
See all 40 libraries.

Datasets

Subtasks

Latest papers with no code

Most implemented Social Latest No code

A Point-Neighborhood Learning Framework for Nasal Endoscope Image Segmentation

no code yet • 30 May 2024

In this paper, we propose a weakly semi-supervised method called Point-Neighborhood Learning (PNL) framework.

 
Paper
Add Code

Twin Deformable Point Convolutions for Point Cloud Semantic Segmentation in Remote Sensing Scenes

no code yet • 30 May 2024

Thanks to the application of deep learning technology in point cloud processing of the remote sensing field, point cloud segmentation has become a research hotspot in recent years, which can be applied to real-world 3D, smart cities, and other fields.

 
Paper
Add Code

CRIS: Collaborative Refinement Integrated with Segmentation for Polyp Segmentation

no code yet • 30 May 2024

Accurate detection of colorectal cancer and early prevention heavily rely on precise polyp identification during gastrointestinal colonoscopy.

 
Paper
Add Code

Reasoning3D -- Grounding and Reasoning in 3D: Fine-Grained Zero-Shot Open-Vocabulary 3D Reasoning Part Segmentation via Large Vision-Language Models

no code yet • 29 May 2024

We design a simple baseline method, Reasoning3D, with the capability to understand and execute complex commands for (fine-grained) segmenting specific parts for 3D meshes with contextual awareness and reasoned answers for interactive segmentation.

 
Paper
Add Code

Parameter-efficient Fine-tuning in Hyperspherical Space for Open-vocabulary Semantic Segmentation

no code yet • 29 May 2024

Since the PEFT strategy is conducted symmetrically to the two CLIP modalities, the misalignment between them is mitigated.

 
Paper
Add Code

Optimizing Split Points for Error-Resilient SplitFed Learning

no code yet • 29 May 2024

Recent advancements in decentralized learning, such as Federated Learning (FL), Split Learning (SL), and Split Federated Learning (SplitFed), have expanded the potentials of machine learning.

 
Paper
Add Code

Organizing Background to Explore Latent Classes for Incremental Few-shot Semantic Segmentation

no code yet • 29 May 2024

During incrementally learning novel classes, the data distribution of old classes will be destroyed, leading to catastrophic forgetting.

 
Paper
Add Code

Lifelong Learning Using a Dynamically Growing Tree of Sub-networks for Domain Generalization in Video Object Segmentation

no code yet • 29 May 2024

However, when DGT is evaluated using in-domain multi-sources, the results show superior performance compared to state-of-the-art video object segmentation and other lifelong learning techniques with an average performance increase in the F-score of 6. 9% with minimal catastrophic forgetting.

 
Paper
Add Code

Enabling Visual Recognition at Radio Frequency

no code yet • 29 May 2024

This paper introduces PanoRadar, a novel RF imaging system that brings RF resolution close to that of LiDAR, while providing resilience against conditions challenging for optical signals.

 
Paper
Add Code

Learning to Detour: Shortcut Mitigating Augmentation for Weakly Supervised Semantic Segmentation

no code yet • 28 May 2024

In this paper, we propose shortcut mitigating augmentation (SMA) for WSSS, which generates synthetic representations of object-background combinations not seen in the training data to reduce the use of shortcut features.

 
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