Can Androids Conceive of Electric Sheep
Explore the journey of creating an android artist, delving into biomechanics, cognition, creativity, and insight simulation. Discover novel applications and thought-provoking questions about artificial artistic expression.
Learning Robust Imaging Models without Paired Data
Explore robust imaging models using Bayesian inference and deep learning without paired data. Learn techniques for image denoising, segmentation, and unpaired degradation modeling in practical applications.
Corona-Net
Explore Corona-Net: an open-source project for COVID-19 diagnosis and symptom segmentation using deep learning models like EfficientNet and U-Net on CT scans.
Honey Bee Conservation Using Deep Learning
Explore DeepBee: an innovative tool using deep learning for automatic honeybee colony assessment, streamlining the process of counting and classifying comb cells for beekeepers.
What and Where? - Machine Learning for Geospatial Image Analysis
Explore machine learning techniques for geospatial image analysis, extracting valuable geographical information from aerial and satellite imagery using deep learning and convolutional neural networks.
Chan Vese Attention U-Net - An Attention Mechanism for Robust Segmentation
Explore an innovative attention mechanism for robust image segmentation using Chan Vese Attention U-Net, enhancing segmentation accuracy and efficiency.
AI-Based Wafer Defect Detection Using Anomaly Detection - Real-Time Implementation
Discover advanced AI techniques for real-time wafer defect detection through unsupervised and semi-supervised learning, focusing on anomaly detection and segmentation in industrial manufacturing environments.
Improving Data and Modeling for Computer Vision Applications
Explore advancements in computer vision for data-centric image classification. Learn about visual prompts, parameter-efficient models, and adapting representations for improved performance and efficiency.
Mid-Level Vision - Lecture 2
Explore advanced concepts in mid-level computer vision, building on foundational knowledge to enhance understanding of visual perception and processing techniques.
UnSAM - Unsupervised Segmentation Anything Model: A New Approach to Image Segmentation
Discover UnSAM: a groundbreaking unsupervised image segmentation model. Learn its divide-and-conquer approach, hierarchical structure discovery, and impressive performance across datasets.
Unveiling Meta's Impressive CV Model - SAM 2: Segment Anything in Images and Videos
Explore Meta's advanced CV model SAM 2, featuring unified architecture for image and video segmentation. Learn its capabilities through demos and code samples for enhanced visual understanding.
Advanced Computer Vision Workflows with Foundation and Custom Models
Build computer vision applications by combining foundation models like Segment Anything 2 with custom trained models like YOLOv8, using Roboflow Workflows for efficient and powerful image processing pipelines.
3D U-Net for Semantic Segmentation
Learn to implement 3D U-Net for semantic segmentation on volumetric data like FIB-SEM, CT, and MRI. Covers data preparation, model architecture, training, and multichannel image processing using Python libraries.
Improving Semantic Segmentation - U-Net Performance via Ensemble of Multiple Trained Networks
Enhance U-Net performance for semantic segmentation using ensemble methods with ResNet34, Inception V3, and VGG16 networks. Includes code, dataset, and practical implementation tips.
Deep Learning in Computer Vision
Explore deep learning in computer vision, from basic concepts to advanced architectures. Learn to design networks that understand images, with practical examples and expert insights.
Overview of Image Segmentation with AI
Explore AI-powered image segmentation techniques, from basic concepts to advanced deep learning structures, and learn steps to create effective models for object identification and edge detection.
Segment Anything Model 2 (SAM 2) - Advanced Image and Video Segmentation
Explore Meta AI's advanced image and video segmentation model SAM 2, its capabilities, and implementation for zero-shot object segmentation tasks.
Leaf Tracking, Counting and Occlusion in Plants Using Artificial Neural Networks
Discover how to implement artificial neural networks for plant leaf analysis, including tracking, counting, and handling occlusion through advanced image processing techniques.
Segment Anything Model (SAM) Explained
Explore SAM, a versatile image segmentation model by Meta AI. Learn about its multitask capabilities, zero-shot transferability, and applications across various scenes and objects.
Machine Vision vs Deep Learning in Cancer Detection
Explore machine vision and deep learning applications in cancer diagnosis, comparing their strengths and limitations. Gain insights into innovative computer-aided methods for analyzing microscopic images of breast cancer tissue.
Object and Bounding Box Detection with Vision Models Using Florence 2
Master object detection and bounding box techniques using Florence 2 vision models, from basic architecture to custom dataset annotation and fine-tuning with LoRA adapters for optimal performance.