Publication

Sample Distillation for Object Detection and Image Classification

Related concepts (32)

Graph Chatbot

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Multiclass classification

In machine learning and statistical classification, multiclass classification or multinomial classification is the problem of classifying instances into one of three or more classes (classifying instances into one of two classes is called binary classification). While many classification algorithms (notably multinomial logistic regression) naturally permit the use of more than two classes, some are by nature binary algorithms; these can, however, be turned into multinomial classifiers by a variety of strategies.

Q-learning

Q-learning is a model-free reinforcement learning algorithm to learn the value of an action in a particular state. It does not require a model of the environment (hence "model-free"), and it can handle problems with stochastic transitions and rewards without requiring adaptations. For any finite Markov decision process (FMDP), Q-learning finds an optimal policy in the sense of maximizing the expected value of the total reward over any and all successive steps, starting from the current state.

Supervised learning

Supervised learning (SL) is a paradigm in machine learning where input objects (for example, a vector of predictor variables) and a desired output value (also known as human-labeled supervisory signal) train a model. The training data is processed, building a function that maps new data on expected output values. An optimal scenario will allow for the algorithm to correctly determine output values for unseen instances. This requires the learning algorithm to generalize from the training data to unseen situations in a "reasonable" way (see inductive bias).

Automatic image annotation

Automatic image annotation (also known as automatic image tagging or linguistic indexing) is the process by which a computer system automatically assigns metadata in the form of captioning or keywords to a . This application of computer vision techniques is used in systems to organize and locate images of interest from a database. This method can be regarded as a type of multi-class with a very large number of classes - as large as the vocabulary size.

Online machine learning

In computer science, online machine learning is a method of machine learning in which data becomes available in a sequential order and is used to update the best predictor for future data at each step, as opposed to batch learning techniques which generate the best predictor by learning on the entire training data set at once. Online learning is a common technique used in areas of machine learning where it is computationally infeasible to train over the entire dataset, requiring the need of out-of-core algorithms.

Azeotropic distillation

In chemistry, azeotropic distillation is any of a range of techniques used to break an azeotrope in distillation. In chemical engineering, azeotropic distillation usually refers to the specific technique of adding another component to generate a new, lower-boiling azeotrope that is heterogeneous (e.g. producing two, immiscible liquid phases), such as the example below with the addition of benzene to water and ethanol. This practice of adding an entrainer which forms a separate phase is a specific sub-set of (industrial) azeotropic distillation methods, or combination thereof.

Stability (learning theory)

Stability, also known as algorithmic stability, is a notion in computational learning theory of how a machine learning algorithm output is changed with small perturbations to its inputs. A stable learning algorithm is one for which the prediction does not change much when the training data is modified slightly. For instance, consider a machine learning algorithm that is being trained to recognize handwritten letters of the alphabet, using 1000 examples of handwritten letters and their labels ("A" to "Z") as a training set.

Fractional freezing

Fractional freezing is a process used in process engineering and chemistry to separate substances with different melting points. It can be done by partial melting of a solid, for example in zone refining of silicon or metals, or by partial crystallization of a liquid, as in freeze distillation, also called normal freezing or progressive freezing. The initial sample is thus fractionated (separated into fractions).

Retort

In a chemistry laboratory, a retort is a device used for distillation or dry distillation of substances. It consists of a spherical vessel with a long downward-pointing neck. The liquid to be distilled is placed in the vessel and heated. The neck acts as a condenser, allowing the vapors to condense and flow along the neck to a collection vessel placed underneath. In the chemical industry, a retort is an airtight vessel in which substances are heated for a chemical reaction producing gaseous products to be collected in a collection vessel or for further processing.

Text-to-image model

A text-to-image model is a machine learning model which takes an input natural language description and produces an image matching that description. Such models began to be developed in the mid-2010s, as a result of advances in deep neural networks. In 2022, the output of state of the art text-to-image models, such as OpenAI's DALL-E 2, Google Brain's , StabilityAI's Stable Diffusion, and Midjourney began to approach the quality of real photographs and human-drawn art.