PinnedUnravelling Single Shot Multi-box Detector (SSD)Introduction In this post, I will talk about Single Shot Multi-box Detector which is used for object detection task. This detector falls into One shot classifiers family. Therefore, this makes it fast and hence useful in real time applications. One of the key characteristics of this algorithm is its ability to…Object Detection8 min readObject Detection8 min read
13 hours agoEfficientNetV2: EfficientNet Strikes AgainEfficientNetV2: Smaller Models and Faster Training — 1. INTRODUCTION The paper introduces a new improvised version of EfficientNets, which are faster and have higher accuracy and parameter efficiency. With their improvised architecture they use progressive learning approach and adaptive regularization to train it. In this article, we will discuss the research paper in great detail. 2. Architecture DesignEfficientnetv 23 min readEfficientnetv 23 min read
4 days agoMysterious EfficientNetsRethinking Model Scaling for Convolutional Neural Networks — 1. Introduction The research paper Rethinking Model Scaling for Convolutional Neural Networks introduces a family of EfficientNet architecture. In the paper, they systematically study model scaling and identify that carefully balancing network depth, width and resolution can lead to better results. The paper introduces a compound scaling method that uniformly scales all…Image Classification7 min readImage Classification7 min read
4 days agoUnderstanding Inception-v3Rethinking the Inception Architecture for Computer Vision — 1. Introduction Rethinking the Inception Architecture for Computer Vision has been one of the most complicated research papers I have read. The paper’s language is very complicated along with its content. It was also difficult to find a detail breakdown of paper on the internet. …Computer Vision6 min readComputer Vision6 min read
Jun 25Treasure of Natural Language Processing(NLP)Machine Translation and Attention — Introduction This post is the part of Treasure of Natural Language Processing(NLP) series. In this series, I try to cover all topics that fall under the NLP (Natural Language Processing) concepts. In this post, I will discuss on the various techniques used to solve the Machine Translation task. The article covers…Deep Learning6 min readDeep Learning6 min read
