Category: Computer Vision

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

Pretraining DINOv2 for Semantic Segmentation

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

Multi-Class Semantic Segmentation using DINOv2

Sovit Ranjan Rath March 24, 2025 2 Comments

In this article, we conduct multi-class semantic segmentation results by training the DINOv2 model. ...

Moondream – One Model for Captioning, Pointing, and Detection

Sovit Ranjan Rath March 17, 2025 0 Comment

In this article, we cover the Moondream model which is a VLM (Vision Language Model) that can be used for image captioning, visual querying, object pointing, and object detection. ...

DINOv2 Segmentation – Fine-Tuning and Transfer Learning Experiments

Sovit Ranjan Rath February 3, 2025 3 Comments

In this article, we simply the semantic segmentation (pixel classification) head of the DINOv2 model and carry out experiments comparing fine-tuning and transfer learning. ...

A Mixture of Foundation Models for Segmentation and Detection Tasks

Sovit Ranjan Rath January 13, 2025 0 Comment

In this article, we explore how several foundation models in VLMs, Image Segmentation, and multi-modal models like CLIP help in open-ended class agnostic segmentation and detection tasks. ...