Semantic Segmentation

5082 papers with code • 120 benchmarks • 303 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
53 papers
8,168
30 papers
2,911
See all 38 libraries.

PlainMamba: Improving Non-Hierarchical Mamba in Visual Recognition

chenhongyiyang/plainmamba 26 Mar 2024

In this paper, we further adapt the selective scanning process of Mamba to the visual domain, enhancing its ability to learn features from two-dimensional images by (i) a continuous 2D scanning process that improves spatial continuity by ensuring adjacency of tokens in the scanning sequence, and (ii) direction-aware updating which enables the model to discern the spatial relations of tokens by encoding directional information.

14
26 Mar 2024

The Need for Speed: Pruning Transformers with One Recipe

skhaki18/optin-transformer-pruning 26 Mar 2024

We introduce the $\textbf{O}$ne-shot $\textbf{P}$runing $\textbf{T}$echnique for $\textbf{I}$nterchangeable $\textbf{N}$etworks ($\textbf{OPTIN}$) framework as a tool to increase the efficiency of pre-trained transformer architectures $\textit{without requiring re-training}$.

9
26 Mar 2024

CoDA: Instructive Chain-of-Domain Adaptation with Severity-Aware Visual Prompt Tuning

Cuzyoung/CoDA 26 Mar 2024

SAVPT features a novel metric Severity that divides all adverse scene images into low-severity and high-severity images.

9
26 Mar 2024

Efficient Video Object Segmentation via Modulated Cross-Attention Memory

amshaker/mavos 26 Mar 2024

Recently, transformer-based approaches have shown promising results for semi-supervised video object segmentation.

7
26 Mar 2024

Optimizing LiDAR Placements for Robust Driving Perception in Adverse Conditions

ywyeli/place3d 25 Mar 2024

The robustness of driving perception systems under unprecedented conditions is crucial for safety-critical usages.

11
25 Mar 2024

3D-EffiViTCaps: 3D Efficient Vision Transformer with Capsule for Medical Image Segmentation

hidneuron/3d-effivitcaps 25 Mar 2024

Our encoder uses capsule blocks and EfficientViT blocks to jointly capture local and global semantic information more effectively and efficiently with less information loss, while the decoder employs CNN blocks and EfficientViT blocks to catch ffner details for segmentation.

0
25 Mar 2024

Segment Anything Model for Road Network Graph Extraction

htcr/sam_road 24 Mar 2024

We propose SAM-Road, an adaptation of the Segment Anything Model (SAM) for extracting large-scale, vectorized road network graphs from satellite imagery.

8
24 Mar 2024

MatchSeg: Towards Better Segmentation via Reference Image Matching

keeplearning-again/matchseg 23 Mar 2024

Few-shot learning aims to overcome the need for annotated data by using a small labeled dataset, known as a support set, to guide predicting labels for new, unlabeled images, known as the query set.

7
23 Mar 2024

Anytime, Anywhere, Anyone: Investigating the Feasibility of Segment Anything Model for Crowd-Sourcing Medical Image Annotations

um2ii/sam_dataannotation 22 Mar 2024

Curating annotations for medical image segmentation is a labor-intensive and time-consuming task that requires domain expertise, resulting in "narrowly" focused deep learning (DL) models with limited translational utility.

1
22 Mar 2024

BSNet: Box-Supervised Simulation-assisted Mean Teacher for 3D Instance Segmentation

peoplelu/bsnet 22 Mar 2024

To generate higher quality pseudo-labels and achieve more precise weakly supervised 3DIS results, we propose the Box-Supervised Simulation-assisted Mean Teacher for 3D Instance Segmentation (BSNet), which devises a novel pseudo-labeler called Simulation-assisted Transformer.

0
22 Mar 2024