Contrastive learning
Contrastive learning is a machine learning approach focused on learning representations by contrasting positive and negative examples, enhancing model accuracy and efficiency.
Self-Supervised Learning
SimMIM (simple masked image modeling)
SimMIM is a method in computer vision that focuses on masked image modeling for enhancing visual understanding in AI systems.
Toolformer
Toolformer is a framework designed to enhance large language models by enabling them to autonomously utilize external tools through natural language interactions. It improves model capabilities by integrating APIs for tasks such as search, calculations, and calendar management.
SimSiam (simple siamese network)
SimSiam is a self-supervised learning framework that employs Siamese networks to facilitate feature extraction without negative samples.
BYOL (bootstrap your own latent)
BYOL (bootstrap your own latent) is a self-supervised learning method in machine learning that enhances representation learning without labeled data.
SEER (self-supervised vision model from Facebook)
SEER is a self-supervised vision model developed by Facebook that enhances image recognition without the need for labeled data.
MoCo (momentum contrast)
MoCo (momentum contrast) is a self-supervised learning framework designed for contrastive representation learning in machine learning.
DINOv2
DINOv2 is a self-supervised learning model designed for visual representation learning, building on its predecessor DINO for improved performance.
VICReg (variance-invariance-covariance regularization)
VICReg is a regularization technique used in machine learning to ensure the learned representations are both invariant to certain transformations and exhibit specific statistical properties.
VideoMAE (masked autoencoder for video)
VideoMAE is a masked autoencoder framework designed for video data, enhancing the ability to encode and reconstruct video sequences using self-supervised learning techniques.