R-CNN 1 — R-CNN takes an input image, extracts around 2000 bottom-up region proposals, These proposed regions are usually selected at multiple scales with different shapes and sizes. Each region proposal will be labeled with a class and a ground-truth bounding box. 2 — Computes features for each proposal using a large…

KL divergence To measure the difference between two probability distributions over the same variable x, a measure, called the Kullback-Leibler divergence, or simply, the KL divergence has been popularly used in the data mining literature. The concept was originated in probability theory and information theory. The KL divergence, which is closely related to…

Overview Adding a branch for predicting an object mask in parallel. ROI Alignment instead of ROI Pooling. Architecture Mask R-CNN, extends Faster R-CNN by adding a branch for predicting segmentation masks on each Region of Interest (RoI), in parallel with the existing branch for classification and bounding box regression. …

Architecture The Faster R-CNN architecture consists of the RPN as a region proposal algorithm and the Fast R-CNN as a detector network. First of all, the model gets the input image and through the backbone CNN gets the feature map. Besides test time efficiency, another key reason using an RPN as…

Overview Apply fully Convolutional networks to the whole image. ROI Pooling: each proposal is pooled into a fixed-size feature map. Classification with a softmax layer. Regression-based bounding box refinement. Architecture A Fast R-CNN network takes as input an entire image and a set of object proposals. 1. The network first processes the…

Requirements Some Requirements that is needed in the main architecture of R-CNN if you are familiar with them you can skip this part :) IOU Intersection over Union (IoU) is used when calculating mAP. It is a number from 0 to 1 that specifies the amount of overlap between the predicted and…

What is Pruning And Why we need it? By increasing amounts of data and computational power, deep learning models have become bigger and deeper to better learn from data. Deploying these large, accurate models to resource-constrained computing environments such as mobile phones, smart cameras, etc poses a few key challenges. Confronting these challenges, a growing body of work has emerged…

Why Use a Database Instead of the File System? Data redundancy — wasted space Update issues — every copy of the data needs to be modified Data inconsistency — sometimes every copy is not modified Data access issues — getting to just the right data Data isolation — pulling all the data from disparate sources together Integrity constraints buried…

In this post, we will learn about residual networks, why we need them, and … Why We need Residuals? Network depth has crucial importance, But Is learning better networks as easy as stacking more layers? This was answered in Deep Residual Learning for Image Recognition paper when you try to add more layers and go…