Goto

Collaborating Authors

Image Understanding


Author Correction: Analysis of the Human Protein Atlas Image Classification competition

#artificialintelligence

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/.


Facebook & Inria Propose High-Performance Self-Supervised Technique for CV Tasks

#artificialintelligence

Researchers from Facebook and the French National Institute for Research in Digital Science and Technology (Inria) have developed a new technique for self-supervised training of convolutional networks used for image classification and other computer vision tasks. The proposed method surpasses supervised techniques on most transfer tasks and outperforms previous self-supervised approaches. "Our approach allows researchers to train efficient, high-performance image classification models with no annotations or metadata," the researchers write in a Facebook blog post. "More broadly, we believe that self-supervised learning is key to building more flexible and useful AI." Recent improvements in self-supervised training methods have established them as a serious alternative to traditional supervised training. Self-supervised approaches however are significantly slower to train compared to their supervised counterparts.


FrugalML switches between APIs to improve image classification and cut costs

#artificialintelligence

Stanford University researchers developed a framework that enables developers to intelligently switch between multiple cloud AI APIs (including those from Google and Microsoft) within a budget constraint. In preliminary experiments, they claim their system -- FrugalML -- typically leads to a more than 50% cost reduction while matching the accuracy of the best single API. Third-party machine learning APIs come with several challenges. One is that companies don't price workloads the same. Moreover, different APIs perform either better or worse on different types of data.


Adobe taps former Pixel exec to build a universal camera app

Engadget

After leaving Google in March, Marc Levoy, the imaging expert who helped create some of the Pixel lineup's most important computational photography features, has landed at Adobe. In an email, the Photoshop-maker said Levoy will "spearhead company-wide technology initiatives focused on computational photography and emerging products, centered on the concept of a universal camera app." Precisely what that universal camera app will entail Adobe hasn't said yet. However, the company notes Levoy will work with its Photoshop Camera, Adobe Research, Sensei and Digital Imaging teams. As The Verge notes, Adobe's Photoshop Camera and Lightroom apps already include camera functionality.


An Industrial Case study on Deep learning image classification

#artificialintelligence

In this post, I am going to explain a end-to-end use case of deep learning image classification in order to automate the process of classifying defective and non-defective castings in foundry. Casting Process: Casting is one of the major manufacturing process in which molten metal is poured in to a cavity called mould and allowed to cool till it gets solidified into product. Casting defects: These are the defects in the cast product occurred during the casting process and they are undesirable.There are many types of defect in casting like blow hole, pin hole, burr, shrinkage defects, mould material defects, pouring metal defects, metallurgical defects etc. Casting defects are undesirable and cause loss to the manufacturer, therefore the quality department have to do visual inspection of the products and separate the defective one from the good castings. The visual inspection is labour intensive and time consuming, therefore Convolution Neural Networks (CNN) could be used to automate this process by image classification. The figure 1. shows the Casting Inspector app developed in this project.



Google AutoML Vision for Image Classification

#artificialintelligence

Google's AutoML lets you train custom machine learning models without having to code Training high-performance deep networks is often a big task especially for those who have less experience in deep learning or AI. Also, we might require GPU in addition to RAM and CPU. I experienced a lot of issues while trying to classify with CNN. What if I said Google AutoML Vision will solve our problems? Yes, AutoML Vision enables us to train custom machine learning models to classify our images according to our own defined labels.


Computer Vision Models That Learn From Language

#artificialintelligence

Any typical successful computer vision model first undergoes pre-training on ImageNet and then proceeds to do the tasks such as classification or captioning of the image. But can the vision models learn more from language? To explore this, two researchers from the University Of Michigan introduced "VirTex", a pretraining approach to learn visual features via language using fewer images. The aim of this work is to demonstrate that natural language can provide supervision for learning transferable visual representations with better data-efficiency than other approaches. Introducing "VirTex": a pretraining approach to learn visual features via language using fewer images.


RGB Matrix Slot Machine #3DThursday #3DPrinting

#artificialintelligence

The display is powered by an #Adafruit Feather and the RGB Matrix FeatherWing. The DIY 3D printing community has passion and dedication for making solid objects from digital models. Recently, we have noticed electronics projects integrated with 3D printed enclosures, brackets, and sculptures, so each Thursday we celebrate and highlight these bold pioneers! Have you considered building a 3D project around an Arduino or other microcontroller? How about printing a bracket to mount your Raspberry Pi to the back of your HD monitor?


3D Hangouts – RGB Matrix Fruit #3DPrinting

#artificialintelligence

The DIY 3D printing community has passion and dedication for making solid objects from digital models. Recently, we have noticed electronics projects integrated with 3D printed enclosures, brackets, and sculptures, so each Thursday we celebrate and highlight these bold pioneers! Have you considered building a 3D project around an Arduino or other microcontroller? How about printing a bracket to mount your Raspberry Pi to the back of your HD monitor? And don't forget the countless LED projects that are possible when you are modeling your projects in 3D!