YOLO-World: Real-Time Open-Vocabulary Object Detection
Paper
• 2401.17270 • Published
• 43
CLIP
-
-
Multimodal Pathway: Improve Transformers with Irrelevant Data from Other Modalities
Paper • 2401.14405 • Published • 13 -
Improving fine-grained understanding in image-text pre-training
Paper • 2401.09865 • Published • 18 -
CatLIP: CLIP-level Visual Recognition Accuracy with 2.7x Faster Pre-training on Web-scale Image-Text Data
Paper • 2404.15653 • Published • 29 -
Multi-Head Mixture-of-Experts
Paper • 2404.15045 • Published • 60 -
Scaling (Down) CLIP: A Comprehensive Analysis of Data, Architecture, and Training Strategies
Paper • 2404.08197 • Published • 29 -
MoDE: CLIP Data Experts via Clustering
Paper • 2404.16030 • Published • 15 -
Jina CLIP: Your CLIP Model Is Also Your Text Retriever
Paper • 2405.20204 • Published • 37 -
An Image is Worth More Than 16x16 Patches: Exploring Transformers on Individual Pixels
Paper • 2406.09415 • Published • 51 -
Differential Transformer
Paper • 2410.05258 • Published • 180 -
Breaking the Memory Barrier: Near Infinite Batch Size Scaling for Contrastive Loss
Paper • 2410.17243 • Published • 92