Concept

Computer vision

Related lectures (32)

Explores machine learning for feature extraction, 3D vision, and neural networks in mobile robotics.

Synthetic Training Data via Generative Models

Explores the benefits of synthetic data in computer vision through generative models mimicking real images with low sim2real gap.

Computer Vision: Historical Insights and Project Inspirations

Explores the historical development of computer vision and inspires innovative project ideas.

Image Classification: Decision Trees & Random Forests

Explores image classification using decision trees and random forests to reduce variance and improve model robustness.

Visual Intelligence: Embodied AI

Explores computer vision in embodied AI, covering object navigation and video generation from single images, with a focus on robustness and precision.

Transformers in Vision

Explores the evolution of visual intelligence models, focusing on Transformers and their applications in computer vision and natural language processing.

Image Processing I

Covers the basics of image processing and its applications in various fields.

Transformers in Vision

Explores Transformers in computer vision, focusing on 'Attention Is All You Need' architecture and its applications in visual tasks.

Robust Vision: Data Augmentation and Ensembling Techniques

Explores data augmentation and ensembling techniques for robust vision, comparing ViT and ResNet models.

Social Image Systems: From Past to Present

Explores the evolution of social image systems, deep learning models, selfies, and biometrics in online platforms.

Course Project Choice

Introduces the course project for CS-503, emphasizing the importance of project selection related to vision and perceptual agents.

Delineation: Techniques and Dynamics

Explores techniques for delineating objects in images, including dynamic programming and live wire methods.

Computer Vision: Fundamentals and Applications

Covers the fundamentals of computer vision, illusions, challenges, applications, and history.

Computer Vision: Recap

Recaps key concepts in computer vision, challenges, opportunities, and upcoming exam details.

Fine-Grained Visual Categorization: Challenges and Solutions

Explores challenges and solutions in fine-grained visual categorization, focusing on computer vision and machine learning.

Edge Detection: Deep Learning Insights

Explores the evolution of edge detection techniques, from Canny to deep learning insights.

Understanding ImageNet Classifiers

Explores the generalization of ImageNet classifiers and the challenges in achieving reliable machine learning models.

Image Recognition: Datasets and Algorithms

Explores a 2019 paper on image recognition, dataset challenges, biases, and the impact of large-scale datasets on deep learning models.

Visual Intelligence: Introduction

Explores visual intelligence, evolution of vision and action, and the ecological approach to visual perception.

Evaluating Machine Accuracy and Robustness on ImageNet

Explores the evaluation of machine and human accuracy and robustness on ImageNet, highlighting progress, challenges, and the need for improvement.

Related lectures (32)

Machine Learning for Feature Extraction

Explores machine learning for feature extraction, 3D vision, and neural networks in mobile robotics.

Synthetic Training Data via Generative Models

Explores the benefits of synthetic data in computer vision through generative models mimicking real images with low sim2real gap.

Computer Vision: Historical Insights and Project Inspirations

Explores the historical development of computer vision and inspires innovative project ideas.

Image Classification: Decision Trees & Random Forests

Explores image classification using decision trees and random forests to reduce variance and improve model robustness.

Visual Intelligence: Embodied AI

Explores computer vision in embodied AI, covering object navigation and video generation from single images, with a focus on robustness and precision.

Transformers in Vision

Explores the evolution of visual intelligence models, focusing on Transformers and their applications in computer vision and natural language processing.

Image Processing I

Covers the basics of image processing and its applications in various fields.

Transformers in Vision

Explores Transformers in computer vision, focusing on 'Attention Is All You Need' architecture and its applications in visual tasks.

Robust Vision: Data Augmentation and Ensembling Techniques

Explores data augmentation and ensembling techniques for robust vision, comparing ViT and ResNet models.

Social Image Systems: From Past to Present

Explores the evolution of social image systems, deep learning models, selfies, and biometrics in online platforms.

Course Project Choice

Introduces the course project for CS-503, emphasizing the importance of project selection related to vision and perceptual agents.

Delineation: Techniques and Dynamics

Explores techniques for delineating objects in images, including dynamic programming and live wire methods.

Computer Vision: Fundamentals and Applications

Covers the fundamentals of computer vision, illusions, challenges, applications, and history.

Computer Vision: Recap

Recaps key concepts in computer vision, challenges, opportunities, and upcoming exam details.

Fine-Grained Visual Categorization: Challenges and Solutions

Explores challenges and solutions in fine-grained visual categorization, focusing on computer vision and machine learning.

Edge Detection: Deep Learning Insights

Explores the evolution of edge detection techniques, from Canny to deep learning insights.

Understanding ImageNet Classifiers

Explores the generalization of ImageNet classifiers and the challenges in achieving reliable machine learning models.

Image Recognition: Datasets and Algorithms

Explores a 2019 paper on image recognition, dataset challenges, biases, and the impact of large-scale datasets on deep learning models.

Visual Intelligence: Introduction

Explores visual intelligence, evolution of vision and action, and the ecological approach to visual perception.

Evaluating Machine Accuracy and Robustness on ImageNet

Explores the evaluation of machine and human accuracy and robustness on ImageNet, highlighting progress, challenges, and the need for improvement.