Learn how Fynd’s Engineering team built a tool that can be used in marketing, social media, ecommerce and more to remove backgrounds accurately

This blog is intended to introduce the reader to the world of background removal and share some of the learnings and challenges that came our way when creating EraseBG. EraseBG is an entirely automated background service that offers high-resolution outputs for free!

So Let’s Get Started!

Deep Dive into Background Removal

Background removal is the process of selecting the foreground subject in an image and erasing the background so that the foreground subject can be placed on a new background. This is done with the help of a mask produced in the removal process as shown below. …


An in-depth summary of Facebook’s amazing Vision Transformer DINO

DINO, a new self supervised system by Facebook AI, is able to learn incredible representations from unlabeled data. Below is a video visualising it’s attention maps and we see the model was able to automatically learn class-specific features leading to accurate unsupervised object segmentation. It was introduced in their paper “Emerging Properties in Self-Supervised Vision Transformers”

Here’s a summary of how it works 👇

TLDR; A Student ViT learns to predict global features in an image from local patches supervised by the cross entropy loss from a momentum Teacher ViT’s embeddings while doing centering and sharpening to prevent…


This blog is intended to introduce the reader to the world of background removal and appreciate some of its challenges. It highlights some of the thoughts that went into creating EraseBG. EraseBG is an entirely automated background service that offers free high-resolution outputs that is set to launch with a brand new website on 30th May, 2021.

So Let’s Get Started!

Section 1: Background Removal and it’s Applications

Background removal is the process of selecting the foreground subject in an image and erasing the background so that the foreground subject can be placed on a new background. This is done with the help of a mask produced…


This blog explains the first Deep Learning based method to tackle the task of image matting.

The Deep Image Matting paper by Xu et al was pivotal in image matting research using deep neural networks to solve some key challenges for the task and setting some important design choices that further works would take inspiration from. The goal of the paper is to take in an input image and a user-specified refinement region and predict an alpha matte, which represents the opacity values in the refinement region. For a in-depth introduction to this task and some of it’s application, have…


In this blog I aim to give a simple interpretation of how a neural network is performing binary and multi-class classification. I explain how binary classifcation is just a kernal trick performed by the network and multi-class classification is simply a search of optimal functions.

Simple 2D Case

Lets say we want to do a binary classifaction where outputs can be either Class 1 or Class 0. Initally our data is non-linearly separated and looks something like:

Fig1: Let the green dots represent 0 and red dots represent 1

The Green Region - G is the target decision boundary such that for all points (x,y) belonging to G our network outputs 0…


I have started doing the new Foundations to Machine Learning course by Bloomberg(https://bloomberg.github.io/foml/#about) and am loving it so far. Here are some notes on a very interesting lecture. I highly recommend people to do this course.

Lecture 5: Excess Risk Decomposition

The main goal of ML is to solve the Bayes decision function which finds a function of inputs that minimises the loss function. When we search over all possible functions this is called Bayes decision function. Usually we restrict ourselves to a hypothesis space. This prevents us from over fitting and makes training much easier. Most famous ML methods…

Rahul Deora

Computer Vision Research Engineer. Personal Blog site: https://bluesky314.github.io/

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store