Discover published sets by community

A class of deep neural networks, most commonly applied to analyzing visual imagery. CNNs are known for their hierarchical pattern in layer connectivity, which leverages the spatial hierarchy in data and provides translation invariance to some degree.

A statistical procedure that uses an orthogonal transformation to convert a set of observations of possibly correlated variables into a set of values of linearly uncorrelated variables. It's used to reduce the dimensionality of image data.

A type of artificial neural network used to learn efficient codings of unlabeled data. An autoencoder is trained to minimize the difference between the input and its reconstruction, and can be used for tasks such as feature learning and denoising images.

An ensemble learning method that constructs multiple decision trees at training time and outputs the class that is the mode of the classes of the individual trees. It is not inherently visual but can be applied to feature vectors extracted from images.

A supervised learning algorithm that can classify cases by finding a separator. SVM works by mapping data to a high-dimensional feature space so that data points can be categorized, even when the data are not otherwise linearly separable.

A non-parametric method used for classification and regression. In k-NN classification, the output is a class membership, determined by the majority vote of the k nearest neighbors of each point.

A system of two neural networks contesting with each other in a zero-sum game framework. They are used in unsupervised machine learning and are based on a game-theoretic scenario. GANs can generate new images that resemble the training set.

The method of transforming the input data into a set of numerical features that can be used for comparison, classification, or other machine learning tasks. Image features could include shapes, textures, colors, and SIFT or SURF descriptors.

A subset of machine learning in artificial intelligence that has networks capable of learning from data that is unstructured or unlabeled. Also known as deep neural learning or deep neural network.

A first-order iterative optimization algorithm for finding a local minimum of a differentiable function. It's used in training neural networks by adjusting the parameters to minimize the loss function.

A fundamental tool in image processing, especially in the fields of feature detection and feature extraction, which aims at identifying points in a digital image at which the image brightness changes sharply.

A flowchart-like tree structure where an internal node represents feature(attribute), branch represents a decision rule, and each leaf node represents the outcome. They can be used to classify images based on extracted features.

An image descriptor used in computer vision and image retrieval. The model involves representing an image as a set of features, which are quantized into a vocabulary of visual words, mimicking the bag of words model used in text.

A computer vision technique to identify and locate objects in images or videos. Object detection models, such as R-CNN, YOLO, and SSD, utilize deep learning algorithms to recognize patterns on images.

A technique in deep learning that blends two images, namely a content image and a style reference image, to create a new image. This is a popular technique that showcases the capabilities of CNNs beyond simple classification tasks.

The electronic conversion of images of typed, handwritten or printed text into machine-encoded text. OCR is a field of research in pattern recognition, machine learning and computer vision.

A machine learning method where a model developed for a task is reused as the starting point for a model on a second task. It is popular in deep learning where pre-trained models are used as the starting point on computer vision tasks.

The process of categorizing and labeling groups of pixels or vectors within an image based on specific rules. Typical machine learning models for image classification include CNNs and pre-trained networks like VGG or ResNet.

A class of neural networks where connections between nodes form a directed graph along a temporal sequence. This allows them to exhibit temporal dynamic behavior. They are not typically used in vision tasks but can be involved in video analysis or visual attention mechanisms.