Glossary Library

Technical GlossaryComputer Vision

Self-Supervised Visual Features

Visual representations learned without labels that can be reused across many downstream vision tasks.

Self-supervised visual features make it possible to learn strong representations from large-scale unlabeled image data. These features can be reused in a wide range of tasks including classification, segmentation, retrieval, and anomaly detection. They are especially valuable in sectors where annotation cost is high. They are among the concepts that fundamentally transformed the representation-learning paradigm in vision.

You Might Also Like

Explore these concepts to continue your artificial intelligence journey.

Glossary Cover

yapay-zeka-temelleri

Representation Learning

An approach in which informative, discriminative, and task-relevant internal representations are learned automatically from raw data.

Glossary Cover

makine-ogrenmesi

Non-negative Matrix Factorization

A dimensionality reduction technique that produces part-based and interpretable representations in non-negative data.

Glossary Cover

makine-ogrenmesi

Autoencoder-Based Dimensionality Reduction

An approach that learns lower-dimensional representations of data through neural-network-based compression.