Computer Code
 
Edit

Semantic Segmentation

5276 papers with code • 126 benchmarks • 313 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
8,294
rwightman/pytorch-image-models
33 papers
30,001
osmr/imgclsmob
30 papers
2,924
open-mmlab/mmsegmentation
19 papers
7,478
See all 39 libraries.

Datasets

Subtasks

Latest papers with no code

Most implemented Social Latest No code

Leveraging Fixed and Dynamic Pseudo-labels for Semi-supervised Medical Image Segmentation

no code yet • 12 May 2024

To this end, we propose a novel approach where multiple pseudo-labels for the same unannotated image are used to learn from the unlabeled data: the conventional fixed pseudo-label and the newly introduced dynamic pseudo-label.

 
Paper
Add Code

Building a Strong Pre-Training Baseline for Universal 3D Large-Scale Perception

no code yet • 12 May 2024

Such inconsiderate consistency greatly hampers the promising path of reaching an universal pre-training framework: (1) The cross-scene semantic self-conflict, i. e., the intense collision between primitive segments of the same semantics from different scenes; (2) Lacking a globally unified bond that pushes the cross-scene semantic consistency into 3D representation learning.

 
Paper
Add Code

In The Wild Ellipse Parameter Estimation for Circular Dining Plates and Bowls

no code yet • 12 May 2024

Ellipse estimation is an important topic in food image processing because it can be leveraged to parameterize plates and bowls, which in turn can be used to estimate camera view angles and food portion sizes.

 
Paper
Add Code

Global Motion Understanding in Large-Scale Video Object Segmentation

no code yet • 11 May 2024

Namely, we focus on integrating scene global motion knowledge to improve large-scale semi-supervised Video Object Segmentation.

 
Paper
Add Code

ADLDA: A Method to Reduce the Harm of Data Distribution Shift in Data Augmentation

no code yet • 11 May 2024

This study introduces a novel data augmentation technique, ADLDA, aimed at mitigating the negative impact of data distribution shifts caused by the data augmentation process in computer vision task.

 
Paper
Add Code

DeVOS: Flow-Guided Deformable Transformer for Video Object Segmentation

no code yet • 11 May 2024

For short-term local propagation, we propose a novel attention mechanism ADVA (Adaptive Deformable Video Attention), allowing the adaption of similarity search region to query-specific semantic features, which ensures robust tracking of complex shape and scale changes.

 
Paper
Add Code

Multi-level Personalized Federated Learning on Heterogeneous and Long-Tailed Data

no code yet • 10 May 2024

Federated learning (FL) offers a privacy-centric distributed learning framework, enabling model training on individual clients and central aggregation without necessitating data exchange.

 
Paper
Add Code

VLSM-Adapter: Finetuning Vision-Language Segmentation Efficiently with Lightweight Blocks

no code yet • 10 May 2024

Foundation Vision-Language Models (VLMs) trained using large-scale open-domain images and text pairs have recently been adapted to develop Vision-Language Segmentation Models (VLSMs) that allow providing text prompts during inference to guide image segmentation.

 
Paper
Add Code

Enhancing Weakly Supervised Semantic Segmentation with Multi-modal Foundation Models: An End-to-End Approach

no code yet • 10 May 2024

Weakly-Supervised Semantic Segmentation (WSSS) offers a cost-efficient workaround to extensive labeling in comparison to fully-supervised methods by using partial or incomplete labels.

 
Paper
Add Code

Zero-shot Degree of Ill-posedness Estimation for Active Small Object Change Detection

no code yet • 10 May 2024

To regularize this problem, we apply the conceptof self-supervised learning to achieve efficient DoI estimationscheme and investigate its generalization to diverse datasets. Specifically, we tackle the challenging issue of obtaining self-supervision cues for semantically non-distinctive unseen smallobjects and show that novel "oversegmentation cues" from openvocabulary semantic segmentation can be effectively exploited. When applied to diverse real datasets, the proposed DoI modelcan boost state-of-the-art change detection models, and it showsstable and consistent improvements when evaluated on real-world datasets.

 
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