Mediaspace scheduled maintenance: Aug 25, 2026 07:00 - 12:00 AM. During this time, videos will be temporarily unavailable. Check status updates.

Lecture

Image Recognition: Datasets and Algorithms

In course

HUM-485: Data in context: Critical Data Studies I

Le cours "Critical Data Studies" s'inscrit dans la nouvelle offre d'enseignements TILT qui propose de croiser des savoirs provenant des SHS et des sciences de l'ingénieur afin d'aborder des thématiques complexes qui nécessitent une méthodologie interdiscip ...

Description

This lecture delves into a 2019 paper proposing a novel approach to image recognition by separating images into shape and appearance components, discussing the datasets used, such as celebrity images, cat head photos, and bird images, and highlighting the challenges and biases in dataset creation. It also explores the impact of large-scale datasets like ImageNet on deep learning models, the importance of ground truths, and the evolution of datasets over time.

Official source

Related concepts (22)

Computer vision

Computer vision tasks include methods for , , and understanding digital images, and extraction of high-dimensional data from the real world in order to produce numerical or symbolic information, e.g. in the forms of decisions. Understanding in this context means the transformation of visual images (the input to the retina in the human analog) into descriptions of the world that make sense to thought processes and can elicit appropriate action.

ImageNet

The ImageNet project is a large visual database designed for use in visual object recognition software research. More than 14 million images have been hand-annotated by the project to indicate what objects are pictured and in at least one million of the images, bounding boxes are also provided. ImageNet contains more than 20,000 categories, with a typical category, such as "balloon" or "strawberry", consisting of several hundred images.

Recurrent neural network

A recurrent neural network (RNN) is one of the two broad types of artificial neural network, characterized by direction of the flow of information between its layers. In contrast to uni-directional feedforward neural network, it is a bi-directional artificial neural network, meaning that it allows the output from some nodes to affect subsequent input to the same nodes. Their ability to use internal state (memory) to process arbitrary sequences of inputs makes them applicable to tasks such as unsegmented, connected handwriting recognition or speech recognition.

Facial recognition system

A facial recognition system is a technology potentially capable of matching a human face from a or a video frame against a database of faces. Such a system is typically employed to authenticate users through ID verification services, and works by pinpointing and measuring facial features from a given image. Development began on similar systems in the 1960s, beginning as a form of computer application. Since their inception, facial recognition systems have seen wider uses in recent times on smartphones and in other forms of technology, such as robotics.

Neural network

A neural network can refer to a neural circuit of biological neurons (sometimes also called a biological neural network), a network of artificial neurons or nodes in the case of an artificial neural network. Artificial neural networks are used for solving artificial intelligence (AI) problems; they model connections of biological neurons as weights between nodes. A positive weight reflects an excitatory connection, while negative values mean inhibitory connections. All inputs are modified by a weight and summed.

Related lectures (38)

Deep Learning: No Free Lunch Theorem and Inductive Bias

Covers the No Free Lunch Theorem and the role of inductive bias in deep learning and reinforcement learning.

Perception: Data-Driven Approaches

Explores perception in deep learning for autonomous vehicles, covering image classification, optimization methods, and the role of representation in machine learning.

NFNets: Removing BatchNorm for High-Performance Image Recognition

Explores NFNets as an alternative to BatchNorm in ResNets, achieving high performance on ImageNet.

Machine Learning Fundamentals

Covers fundamental principles, opportunities, and challenges in machine learning.

The Hidden Convex Optimization Landscape of Deep Neural Networks