Kunal Dawn

Enhancing Image Segmentation using U2-Net: An Approach to Efficient Background Removal

U2-Net (popularly known as U2-Net) is a simple yet powerful deep-learning-based semantic segmentation model that revolutionizes background removal in image segmentation. Its effective and straightforward approach is crucial for applications

Background Estimation, Image Segmentation, PyTorch, Segmentation

GradCAM – Enhancing Neural Network Interpretability in the Realm of Explainable AI

With millions of trainable parameters, neural networks have long been considered black boxes. They can produce stunning results, and we often accept the output with very little understanding as to

CNN, Deep Learning, PyTorch-Lightning

Comparing KerasCV YOLOv8 Models on the Global Wheat Data 2020

This article is a continuation of our series of articles on KerasCV. The previous article discussed fine-tuning the popular DeeplabV3+ model for semantic segmentation. In this article, we will shift

Keras, Object Detection, Tensorflow, YOLO

Semantic Segmentation using KerasCV DeepLabv3+

Fine-tuning DeepLabv3+ from KerasCV for Semantic Segmenation

Image Segmentation, Keras, Segmentation, Tensorflow

Animal Pose Estimation: Fine-tuning YOLOv8 Pose Models

In this article, fine-tune the YOLOv8 Pose model for Animal Pose Estimation.

keypoint detection, Keypoint Estimation, Pose Estimation, YOLO

Object Keypoint Similarity in Keypoint Detection

In the constantly evolving field of computer vision, understanding the precise structure and pose of objects is essential. Whether it’s detecting a specific object in a cluttered scene or analyzing

keypoint detection, Keypoint Estimation, Similarity Measure