Click the "Xiaobai Learns Vision" above, select to add "Star" or "Top" Heavyweight content delivered to you first Editor’s Recommendation Object Detection is a popular direction in the field of Computer Vision, widely used in autonomous driving, industrial inspection, video surveillance, and aerospace, among others. Its basic process involves locating the target of interest in … Read more
Source｜Heart of Autonomous Driving Image segmentation in computer vision is an important subfield that aims to assign each pixel in an image to different categories or objects. This technology is widely used in various applications such as image recognition, scene understanding, and medical image processing, demonstrating significant practical value. Previously, there were roughly two methods … Read more
In previous articles, we have introduced two types of image segmentation loss functions. Today, we will share commonly used multi-class image segmentation loss functions such as multi-class cross-entropy, weighted multi-class cross-entropy, multi-class Dice coefficient, multi-class Focal Loss, etc., and provide code to reproduce the above loss functions in TensorFlow. 1. Cross Entropy The cross-entropy loss … Read more
Commonly used image segmentation loss functions include binary cross-entropy, dice coefficient, Tversky, and Focal Loss. Today, I will reproduce the above loss functions in TensorFlow and compare the results. 1. Cross Entropy The cross-entropy loss function compares the predicted class values with the target values on a pixel-by-pixel basis, and then averages the values over … Read more
Author / Li Xi 0 Introduction This article organizes previous research on multimodal visual structure learning from a new perspective, focusing on the characteristics and applications of spherical panoramic images. Spherical images are mostly related to fisheye or 360° panoramic views, containing a wealth of structural knowledge, primarily aimed at applications such as autonomous driving, … Read more
Reprinted from: Jishi Platform As one of the representative algorithms of deep learning, Convolutional Neural Networks (CNN) have achieved the best results in fields such as computer vision. In 1998, Yann LeCun proposed LeNet-5, applying the BP algorithm to train the neural network structure, forming the prototype of contemporary CNNs. In 2012, during the ImageNet … Read more
Click the "Xiaobai Learns Vision" above, select to add "Star" or "Top" Heavy content delivered at the first time Author丨Vinithavn Source丨AI Park 1. Introduction What is Object Detection? Given an image, we humans can identify objects within it. For example, we can detect if there are cars, trees, people, etc., in the image. If we … Read more
Since the launch of the SAM “Segment Anything” model, a wave of creative works has begun, with ideas and actions emerging! The developer from PaddlePaddle AI StudioThe Singing Alchemist has created an evolved version of SAM, integrating SAM and Stable Diffusion to achieve both “segmentation” and “generation” capabilities in one application, which is available for … Read more
Click the above “Beginner’s Guide to Computer Vision”, select “star” or “pin” Heavyweight content delivered promptly Author: Rédigé par Gabriel Guerin Translated by: ronghuaiyang Source: AI Park Introduction In some cases, collecting data from various scenes can be challenging. This article presents a method. Deep learning models require a significant amount of data to achieve … Read more
This article will cover the essence of U-Net principles of U-Net and its applications in three aspects to help you understand the image segmentation network | U-Net. U-Net 1. U-Net essence Definition of U-Net:A convolutional neural network based on deep learning, mainly used for image segmentation tasks, especially the segmentation of biomedical images.It consists of … Read more