Blog: 2 Columns

A successful marketing plan relies heavily on the pulling-power of advertising copy. Writing result-oriented ad copy is difficult.

Home

Blog

Machine Learning

PSOL for Weakly Supervised Object Localization

Object localization and object detection are well-researched computer vision problems. The main task of these methods is to locate instances of a particular object category in an image by using tightly cropped bounding boxes centered on the instances. Supervised models which are using rich annotated images for training have very successful results. However obtaining detailed image annotations, e.g. bounding boxes, is both expensive and often subjective. On the other hand, weakly-supervised object localization (WSOL) methods have increasing popularity, since they are promising to train localization models with only image-level labels (e.g. class labels).

Dec 21, 2020

by

The Usage of CycleGAN for Image Translation to Increase the Size of Fridge Food Types Dataset

CycleGAN models are used for image-to-image translation tasks like translating photographs of horsesto zebra or apples to oranges, and the reverse.We investigate model architectures, loss functions and training sets to determine the optimal combinationfor translating blender fridge images into a more realistic version of a fridge.

Dec 19, 2020

by

Deep Learning

A case for custom deep learning solutions

AWS Rekognition and Azure Computer Vision module are two very popular and widely used deep learning platforms for Computer Vision. Both of these platforms can identify a wide range of objects like natural objects, human body and face, household things, animals, birds, vehicles, gadgets, food items and more, in an image with very good accuracy. Their ability to identify a variety of natural and man-made objects at pretty decent accuracy, with models that work right out of the box without the need for any training, make them a good choice for many deep learning computer vision applications. But are they good enough for all kinds of real-world applications or does specialised deeplearning solutions have a case?

Dec 17, 2020

by

Computer Vision Research

Veggie Doneness Model For Smart Oven

This blog explores a solution that aims to develop and train a CNN classified that can detect the level of doneness of veggies while being cooked in a smart oven. One of the major difficulties in this project was finding in-oven images of vegetable trays.

Dec 2, 2020

by

Mayssam Naji