Popular articles by tonypetrov
The objective of our task is extract parent-subsidiary relationship in text. For example, a news from techcruch says this, ‘Remember those rumors a few weeks ago that Google was looking to acquire the plug-and-play security camera company, Dropcam? Yep. It just happened.’. Now from this sentence we can infer that Dropcam is a subsidiary of Google. But there are million of companies and several million articles talking about them. A Human being can be tired of doing even 10! Trust me 😉 We have developed some cool Machine learning models spanning from classical algorithms to Deep Neural network do this for you. There is a bonus! We just do not give you probabilities. We also give out that sentences that triggered the algorithm to make the inference! For instance when it says Orcale Corp is the parent of Microsys it can also return that the sentence in its corpus ‘Oracle Corp’s Microsys customer support portal was seen communicating with a server’, triggered its prediction.
Our best model (derived from VGG) achieved 99.46% top3 accuracy (90.18% top1) with processing time during training of 0.006 s per image on a single GPU Titan X (200s / epoch with 37 000 images).
The teams vision is for the team members to see where they stand compared to others in terms of ideas and approaches to computer vision and to learn new ideas and approaches from the other team-mates and the mentors.
Therefore the team is pursuing a pure computer vision approach to solving the Kaufland and/or the ReceiptBank cases.
In this article we present our solution for helping customers and making their shopping experience easier while identifying products from images. We bring forward our idea and discuss the results of our CV experiment.
Many big retailers offer in store a rapidly growing variety of fresh produce from local and global sources, such as fruit and vegetables that need to be weighed quickly and effortlessly to mark their quantity and respective price. Smart scales that use image recognition to optimise user experience and allow additional features, such as e.g. cooking recipes can provide a new solution to this problems. The solution we provide to the Kaufland case includes training a Convolutional Neural Network (CNN) with GoogLeNet architecture on the original Kaufland data set and fine-tuning it with a Custom Training Set we have created, achieving the following results (Kaufland Case Model #13): training accuracy: Top-1: 91%, Top-5: 100%; validation accuracy: Top-1: 86.1% , Top-5: 99%, and TEST dataset accuracy of: Top-1: 86.1%, Top-5: 99.2%. We have also created another model (Kaufland Case Model #14) by combining similar categories, achieving: training accuracy: Top-1: 96%, Top-5: 100%; validation accuracy: Top-1: 92.5%, Top-5: 100%, and TEST dataset accuracy: Top-1: 91.3%, Top-5: 100%. All trainings were done on our NVIDIA DGX Station training machine using BVLC Caffe and the NVIDIA DIGITS framework. In our article we show visualisations of our numerous trainings, provide an online demo with the best classifiers, which can be further tested. During the final DSS Datathon event we plan to show a live food recognition demo with one of our best models running on a mobile phone . Demo URL: http://norris.imagga.com/demos/kaufland-case/
A simple approach using neural networks.
I’m learning data science, and this is my first experiment with Neural Networks.
The accuracy is about 2.78%, because we have over 50 categories in the training dataset
Thank you for your support. This is an amazing competition.
Case Kaufland¶ On 22.01.2018 Amazon opened Amazon Go – their first ever physical store without cashiers and checkout lines – customers just grab the products from the shelves and go. AI algorithms detect what product you have grabbed. Kaufland offers the unique opportunity to work with their internal data on a similar problem – developing […]
Popular comments by tonypetrov
Overall you show great understanding of the problem and the data itself. The structure of the article is well formed. However there are a few areas in which you can improve.
First in your evaluation don’t just add the list of pairs. It is very difficult to tell if which is the parent of which just by looking at the list. Especially if you’ve never heard of Danaher_Corporation and Pall_Corporation. Who’s the parent and who’s the subsidiary? Was your model correct in predicting this relationship? Add for instance your precision or recall values or add a confusion matrix? Also among these pairs which did the algorithm misclassify and in your opinion why?
Second and this one is really minor so don’t worry much about it. If you add an abstract don’t make it too detailed. Abstracts are for people who are not experts and are not familiar with NLP. It should be a simple layman’s description of what the problem is and how you propose to solve it. Leave the detailed description for the Introduction.
You’ve presented your solution and test results very well. However you shouldn’t just copy the case description as a business understanding. In this section you need to show that you understand what the problem is, who the users of your solution are, and what they expect to see from the system. Good presentation overall and a very interesting article to read. Well done Team Cherry!!
Good first attempt. I think you can improve on your Neural network architecture. Read more about convolutional neural networks they are a great help with image recognition tasks
(+) Well formed article, shows understanding of the problem and task at hand
(+) You’ve handled the insufficient data problem well and you’ve presented a good description of the model
(-) Providing raw results is not very helpful you should add some analysis as to why you think you got the results that you have.
(~) Also would be nice to know more about the actual performance of the models. The most accurate model is not always the best choice especially if it requires expensive hardware to run and you don’t have the budget for it.
You show good understanding of the data set and the challenges that it represents.
You’ve managed to find an interesting workaround some of the issues mainly orientation and lighting.
However there are some areas that you can improve in. First is the business understanding. You need to show that you have understood the problem domain and who the final users of the system will be. What their expectations are? In the model section you make a very good argument as to why you’ve decided to use GoogleLenet, however you could go into more details about the advantages and disadvantages of using this tech as opposed to other solutions. In the evaluation section you need to provide an analysis of the results showing that you understand the inner workings of your system, not just raw results.
Also you should never provide the results from the training and validation sets
as those are considered training data and the results on them are misleadingly high, due to the fact that the system has seen them before. You should always have a separate set of data for testing purposes.