Category: Computer Vision

Computer Vision in AI encompasses various tasks including classical computer vision, deep learning based image classification, image classification, object detection etc.

Background Replacement Using BiRefNet

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. ...

Introduction to BiRefNet

Sovit Ranjan Rath September 15, 2025 2 Comments

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. ...

Semantic Segmentation using Web-DINO

Sovit Ranjan Rath June 30, 2025 0 Comment

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. ...

Web-SSL: Scaling Language Free Visual Representation

Sovit Ranjan Rath June 16, 2025 0 Comments

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

Pretraining DINOv2 for Semantic Segmentation

Sovit Ranjan Rath March 31, 2025 0 Comment

In this article, we are pretraining the DINOv2 model for semantic segmentation on the COCO 2017 dataset and running inference on images and videos. ...