Contrastive Learning
Training by pulling matching pairs together and pushing others apart.
Visão geral
Contrastive learning trains an encoder so that representations of matching pairs are close and representations of non-matching pairs are far apart. It solves the problem that labelled data is scarce, because a match can be defined by augmentation, co-occurrence or a paired modality rather than by a human. It exists as the objective behind most embedding models, including the image-text pairs CLIP is trained on.
Grafo de tecnologias
Como Contrastive Learning se liga ao resto do stack.
Aplicado a
- CLIP model Multimodal Contrastive Learning used for CLIP High ✓ source
- Embedding concept Techniques Contrastive Learning used for Embedding High ✓ source
- LAION-5B dataset Datasets LAION-5B used for Contrastive Learning High ✓ source
- Sentence Transformers framework Frameworks Contrastive Learning used for Sentence Transformers High ✓ source