DINO is a self-supervised learning (SSL) framework that uses the Vision Transformer (ViT) as it's core architecture. While SSL initially gained popularity through its use in natural language ...
Sapiens: Foundation for Human Vision Models by Meta
Sapiens, a family of foundational Human Vision Models by Rawal et al., from Meta, achieves state-of-the-art results for human centric tasks like 2D pose estimation, body-part segmentation, depth ...
ColPali: Enhancing Financial Report Analysis with Multimodal RAG and Gemini
ColPali multimodal RAG offers a novel approach for efficient retrieval of elements such as images, tables, charts, and texts by treating each page as an image. This method takes advantage of Vision ...
Handwritten Text Recognition using OCR
Handwritten text documents are ubiquitous in the field of research and study. They are personalized to the user’s needs and often contain a style of writing difficult to comprehend by others. This ...
Training CLIP Model from Scratch for an Image Retrieval App
Contrastive Language Image Pretraining (CLIP) by OpenAI is a model that connects text and images, allowing it to recognize and categorize images without needing specific training for each category. ...
Recommendation System using Vector Search with Qdrant
Suppose you watched Black Panther on Netflix over the weekend and now want to check out more films like that. When you open Netflix again, it suggests Iron Man, Avengers, and Doctor Strange. This is ...
