Skip to main content
aegean.ai home page
Search...
⌘K
GitHub
LinkedIn
Search...
Navigation
Remote Sensing
Segment Anything Model (SAM)
Home
Products
Book
Courses
Media
Blog
Careers
About
Overview
Overview
Remote Sensing
Remote Sensing
Introduction
Lakehouse
DeepLabV3+
Mask R-CNN
SAM
Training Pipelines
Dataset Processing
Metrics Report
Pipeline Architecture
NJ Results
Manufacturing QC
Manufacturing Quality Control
Software Architecture
Domain Model
Data Analysis
The Seamagine Dataset
Edge & Line Feature Extraction
Quantifying Pixel-level Information
The Unsupervised Approach
Pretrained Models
Pretrained CNN
Optimizing Embedding Dimensions
Finetuned CNN
Pretrained CLIP
PatchCore
EfficientAD
Self-Supervised Learning
The Supervised Approach
Model Training Pipeline
Model Evaluation & Verification Pipeline
CIFAR-10 Verification
MVTec-AD Verification
Inference Pipeline
The Cold Start Problem in Production
CLI Reference
Milestones
Experiment Tracking
Backbone Networks
Remote Sensing
Segment Anything Model (SAM)
Using prompting to improve segmentation with the Segment Anything Model.
This section is under development. SAM integration for sidewalk detection is being explored as an enhancement to our current DeepLabV3+ pipeline.
Edit this page on GitHub
or
file an issue
.
Connect these docs
to Claude, VSCode, and more via MCP for real-time answers.
Detectron2's Mask R-CNN Model
Previous
Enhancing Training / Finetuning Pipelines
Next
⌘I