Skip to content

PaperCodex

Subscribe

Semantic Segmentation

LSKNet: A Lightweight, High-Performance Backbone for Remote Sensing Object Detection, Segmentation, and Classification

LSKNet: A Lightweight, High-Performance Backbone for Remote Sensing Object Detection, Segmentation, and Classification 639

Remote sensing imagery—captured from satellites, drones, or aircraft—presents unique challenges for computer vision systems. Objects are often small, densely packed,…

01/13/2026Image Classification, Remote Sensing Object Detection, Semantic Segmentation
Lite-HRNet: High-Accuracy Human Pose Estimation and Semantic Segmentation with Minimal Compute

Lite-HRNet: High-Accuracy Human Pose Estimation and Semantic Segmentation with Minimal Compute 894

When building real-time vision applications for mobile, embedded, or edge devices, developers often face a tough trade-off: accuracy versus efficiency.…

01/13/2026Human Pose Estimation, Lightweight Neural Networks, Semantic Segmentation
IDRNet: Boost Semantic Segmentation Accuracy with Smarter Context Modeling—No Heavy Priors Required

IDRNet: Boost Semantic Segmentation Accuracy with Smarter Context Modeling—No Heavy Priors Required 876

If you’re building computer vision systems that rely on pixel-perfect understanding—like autonomous driving, medical imaging analysis, or retail scene parsing—you’ve…

01/13/2026Context Modeling, Dense Prediction, Semantic Segmentation
VMamba: A Linear-Time Vision Backbone for High-Resolution, Scalable Computer Vision Tasks

VMamba: A Linear-Time Vision Backbone for High-Resolution, Scalable Computer Vision Tasks 2969

In the rapidly evolving landscape of computer vision, model efficiency and scalability are no longer optional—they’re essential. Enter VMamba, a…

12/26/2025Image Classification, Object Detection, Semantic Segmentation
OMG-Seg: One Unified Model for All Segmentation Tasks—No More Fragmented Pipelines

OMG-Seg: One Unified Model for All Segmentation Tasks—No More Fragmented Pipelines 1338

For years, computer vision practitioners have juggled a patchwork of specialized models to tackle different segmentation tasks—semantic, instance, panoptic, video,…

12/26/2025Instance Segmentation, Panoptic Segmentation, Semantic Segmentation
MambaVision: Achieve SOTA Image Classification & Downstream Vision Tasks with Hybrid Mamba-Transformer Efficiency

MambaVision: Achieve SOTA Image Classification & Downstream Vision Tasks with Hybrid Mamba-Transformer Efficiency 1946

If you’re building computer vision systems that demand both high accuracy and real-world efficiency—without getting bogged down in architectural complexity—MambaVision…

12/26/2025Image Classification, Object Detection, Semantic Segmentation
FlexiViT: One Vision Transformer for All Patch Sizes—Deploy Faster or More Accurate Models Without Retraining

FlexiViT: One Vision Transformer for All Patch Sizes—Deploy Faster or More Accurate Models Without Retraining 3276

Vision Transformers (ViTs) have become a cornerstone of modern computer vision, offering strong performance across a wide range of tasks.…

12/22/2025Image Classification, Image-text Retrieval, Semantic Segmentation
FastViT: Achieve State-of-the-Art Speed and Accuracy for Vision Tasks on Mobile and Edge Devices

FastViT: Achieve State-of-the-Art Speed and Accuracy for Vision Tasks on Mobile and Edge Devices 1974

FastViT is a high-performance hybrid vision transformer designed to deliver exceptional speed and accuracy—especially on resource-constrained platforms like mobile phones…

12/22/2025Image Classification, Object Detection, Semantic Segmentation
AM-RADIO: Unify Vision Foundation Models into One High-Performance Backbone for Multimodal, Segmentation, and Detection Tasks

AM-RADIO: Unify Vision Foundation Models into One High-Performance Backbone for Multimodal, Segmentation, and Detection Tasks 1357

In modern computer vision, practitioners often juggle multiple foundation models—CLIP for vision-language alignment, DINOv2 for dense feature extraction, and SAM…

12/19/2025Object Detection, Semantic Segmentation, Vision-language Understanding
CARAFE: Boost Dense Prediction Accuracy with Content-Aware, Lightweight Feature Upsampling

CARAFE: Boost Dense Prediction Accuracy with Content-Aware, Lightweight Feature Upsampling 32164

Feature upsampling is a critical but often overlooked component in modern computer vision pipelines. Whether you’re building an object detector,…

12/18/2025Instance Segmentation, Object Detection, Semantic Segmentation

Posts pagination

1 2 Next
Copyright © 2026 PaperCodex.
  • Facebook
  • YouTube
  • Twitter

PaperCodex