PP-LiteSeg is a lightweight encoder-decoder architecture designed for real-time semantic segmentation. It consists of three modules: Encoder: Lightweight network Aggregation: Simple Pyramid Pooling Module (SPPM) Decoder: Flexible and Lightweight Decoder (FLD) and Unified Attention Fusion Module (UAFM) Encoder The STDCNet is the encoder for the proposed PP-LiteSeg for its high performance. The research paper presents…
In this tutorial, we are going to learn how to use deep learning to remove background from images with TensorFlow. In short, we’ll use DeepLabV3+, a semantic segmentation based model to extract the background and foreground mask from the image. We are going to use these masks to extract the background from the image and…
In this article, we are going to implement the most widely used image segmentation architecture called UNET. We are going to replace the UNET encoder with the VGG16 implementation from the TensorFlow library. The UNET encoder would learn the features from scratch, while the VGG16 is already trained on the Image ImageNet classification dataset. Therefore…
The Squeeze and Excitation network is a channel-wise attention mechanism that is used to improve the overall performance of the network. In today’s article, we are going to implement the Squeeze and Excitation module in TensorFlow and PyTorch. What is Squeeze and Excitation Network? The squeeze and excitation attention mechanism was introduced in the year…
Convolutional Neural Network (CNN) has been most widely used in the field of computer vision and visual perception to solve multiple tasks such as image classification, semantic segmentation and many more. However, there is a need for approaches that can further improve its performance. One such approach is to add some attention mechanism to an…
Deep neural networks have become popular due to their high performance in real-world applications, such as image classification, speech recognition, machine translation and many more. Over time deep neural networks are becoming deeper and deeper to solve more complex tasks. Adding more layers to a deep neural network can improve its performance, but up to…
Transfer Learning is a technique in machine learning where we reuse a pre-trained model to solve a different but related problem. It is one of the popular methods to train the deep neural network. It is generally used for image classification tasks where the amount of the dataset is small. In this article, we will…
In this article, you will learn to perform person segmentation with DeepLabV3+ architecture on human images. Here, we will cover the entire process of image segmentation starting from data processing to evaluation. The entire code is written in Python programming language using TensorFlow 2.5 framework. Table of Content What is image segmentation? Person segmentation dataset.…
In our previous tutorials – cv2.imread() – Read Image using OpenCV Python and cv2.resize() – Resizing Image using OpenCV Python, we have learned to read and resize an image. We will now learn to save the array into an image file. For this, we are going to use cv2.imwrite() function from the OpenCV library. To…
This tutorial focuses on implementing the image segmentation architecture called Deep Residual UNET (RESUNET) in the PyTorch framework. It’s an encoder-decoder architecture developed by Zhengxin Zhang et al. for semantic segmentation. It was initially used for road extraction from high-resolution aerial images in the field of remote sensing image analysis. Original Paper: Road Extraction by Deep Residual U-Net RESUNET…
Nikhil Kumar Tomar
AI Researcher and a part-time blogger and YouTuber. Most of my research is focused medical imaging.
