Category: Computer Vision

In this article, we explore DINOv3 for image classification on a card image classification dataset. We cover the DINOv3 models, the model code, training, and inference. ...

In this article, we create a background replacement application using BiRefNet. We cover the code using Jupyter Notebook and create a Gradio application as well. ...

In this article, we explore the BiRefNet model for high-resolution dichotomous segmentation. Along with discussing the key elements of the paper, we also create a small background removal codebase usign the pretrained model. ...

In this article, we are modifying the Web-DINO 300M architecture for semantic segmentation. We will add a simple segmentation decoder head and train the model for person segmentation. ...

In this article, we explore the Web-DINO models trained via Web-SSL 2.0 methodology on the MC-2B (MetaCLIP-2B) dataset. ...