SLIP: Self-supervision Meets Language-Image Pre-training

Computer Science

• Self-Supervised Learning 100%
• Supervised Learning 33%
• Visual Representation 33%
• Representation Learning 33%
• Performance Compare 33%
• Learning Framework 33%
• Training Dataset 33%
• Multitask Learning 33%
• Vision Transformer 33%

Keyphrases

• Language-Image Pre-training 100%
• Linear Accuracy 33%
• Shooting Accuracy 33%
• Linear Languages 33%