In this paper, we propose an algorithm for fully automatic neural face swapping in images and videos. To the best of our knowledge, this is the first method capable of rendering photo-realistic and temporally coherent results at megapixel resolution.To this end, we introduce a progressively trained multi-way comb network and a light- and contrast-preserving blending method.We also show that while progressive training enables generation of high-resolution images, extending the architecture and training data beyond two people allows us to achieve higher fidelity in generated expressions. When compositing the generated expression onto the target face, we show how to adapt the blending strategy to preserve contrast and low-frequency lighting.Finally, we incorporate a refinement strategy into the face landmark stabilization algorithm to achieve temporal stability, which is crucial for working with high-resolution videos. We conduct an extensive ablation study to show the influence of our design choices on the quality of the swap and compare our work with popular state-of-the-art methods. Read More
Monthly Archives: August 2020
3 Lessons from Chinese Firms on Effective Digital Collaboration
Collaboration between organizations has never been more important. In the face of the current pandemic, a collaborative approach can help address market failures resulting from information asymmetry, misaligned incentives, or a lack of market intermediaries. Yet many companies restrict their partnerships to formal mechanisms such as joint ventures, limiting the extent of their collaboration.
Useful inspiration can come from China, where Covid-19 is but one of many crises that businesses have faced, and where a variety of pressures and opportunities have shaped a set of distinctive partnering practices. Through its rapid transformation from an economy lacking in basic commercial infrastructure to an e-commerce pioneer, China has emerged as a laboratory for developing new collaboration strategies. Read More
How to get your data scientists and data engineers rowing in the same direction
In the slow process of developing machine learning models, data scientists and data engineers need to work together, yet they often work at cross purposes. As ludicrous as it sounds, I’ve seen models take months to get to production because the data scientists were waiting for data engineers to build production systems to suit the model, while the data engineers were waiting for the data scientists to build a model that worked with the production systems.
A previous article by VentureBeat reported that 87% of machine learning projects don’t make it into production, and a combination of data concerns and lack of collaboration were primary factors. On the collaboration side, the tension between data engineers and data scientists — and how they work together — can lead to unnecessary frustration and delays. While team alignment and empathy building can alleviate these tensions, adopting some developing MLOps technologies can help mitigate issues at the root cause. Read More
How Do Data Science Machine Learning And Artificial Intelligence Overlap
In conjunction with data science and digital transformation, you have probably heard the terms of artificial intelligence, machine learning, and deep learning is used. You might wonder what the relationship between those topics is. How do companies in industries range from biopharma to chemicals to food & beverage that incorporate AI, machine learning, and data science to enhance their processes? AI and machine learning allow applications such as virtual digital assistants, facial recognition, and self-driving cars, as well as improvements in healthcare diagnostics and process manufacturing. Are you interested in making a career in these? There are many AI certification courses, data science certification courses, and ML certifications available online. Check out! Read More
A critical analysis of metrics used for measuring progress in artificial intelligence
Comparing model performances on benchmark datasets is an integral part of measuring and driving progress in artificial intelligence. A model’s performance on a benchmark dataset is commonly assessed based on a single or a small set of performance metrics. While this enables quick comparisons, it may also entail the risk of inadequately reflecting model performance if the metric does not sufficiently cover all performance characteristics. Currently, it is unknown to what extent this might impact current benchmarking efforts. To address this question, we analysed the current landscape of performance metrics based on data covering 3867 machine learning model performance results from the web-based open platform ‘Papers with Code’. Our results suggest that the large majority of metrics currently used to evaluate classification AI benchmark tasks have properties that may result in an inadequate reflection of a classifiers’ performance, especially when used with imbalanced datasets. While alternative metrics that address problematic properties have been proposed, they are currently rarely applied as performance metrics in benchmarking tasks. Finally, we noticed that the reporting of metrics was partly inconsistent and partly unspecific, which may lead to ambiguities when comparing model performances. Read More
The Future of Cybersecurity in the Hands of AI
Globally, the AI cybersecurity job market will witness 3.5 million unfilled cybersecurity jobs by 2021 according to The New York Times. Plus, the market size is predicted to reach USD 30.5 billion by 2025.
A recent Synack Report claims that combining cybersecurity talent and AI-enabled technology results in 20x more effective attack surface coverage than traditional methods.
But it’s difficult to truly understand the implication of these numbers. Most content on the topic leaves the reader to do all the math, connect the dots, and try to understand the real problem behind the numbers, all by themselves – an overwhelming task. Read More
Sentiment Analysis using Deep Learning
The growth of the internet due to social networks such as Facebook, Twitter, Linkedin, Instagram etc. has led to significant users interaction and has empowered users to express their opinions about products, services, events, their preferences among others. It has also provided opportunities to the users to share their wisdom and experiences with each other. The faster development of social networks is causing explosive growth of digital content. It has turned online opinions, blogs, tweets, and posts into a very valuable asset for the corporates to get insights from the data and plan their strategy. Read More
Microsoft wants TikTok for the same reason the U.S. fears China
It’s been a month since U.S. Secretary of State Mike Pompeo said the Trump administration was considering banning TikTok. Plenty has happened since, but the situation really accelerated last weekend. In the span of a couple hours, we learned that President Trump was planning to sign an order directing China’s ByteDance to divest its ownership of TikTok and that Microsoft and ByteDance had offered the White House a deal to keep TikTok in the U.S.
Chaos ensued. Trump gave Microsoft 45 days to seal a TikTok deal. Microsoft confirmed it was interested in TikTok’s U.S., Canada, Australia, and New Zealand operations. Trump issued a September 15 sell-by deadline for TikTok and declared he was fine with Microsoft buying TikTok, but that the U.S. government should get a “substantial amount of money” as part of the deal. Finally, yesterday we learned that Microsoft might be pursuing TikTok’s global operations, and Trump signed an executive order to block all U.S. transactions with ByteDance (and Tencent) starting September 20.
What is all this really about? It’s about AI, data, and power. Read More
Consistent Estimators for Learning to Defer to an Expert
Learning algorithms are often used in conjunction with expert decision makers in practical scenarios, however this fact is largely ignored when designing these algorithms. In this paper we explore how to learn predictors that can either predict or choose to defer the decision to a downstream expert. Given only samples of the expert’s decisions, we give a procedure based on learning a classifier and a rejector and analyze it theoretically. Our approach is based on a novel reduction to cost sensitive learning where we give a consistent surrogate loss for cost sensitive learning that generalizes the cross entropy loss. We show the effectiveness of our approach on a variety of experimental tasks. Read More
Facebook’s ‘Red Team’ Hacks Its Own AI Programs
Attackers increasingly try to confuse and bypass machine-learning systems. So the companies that deploy them are getting creative, spending heavily in recent years to deploy AI systems for tasks such as understanding the content of images or text.
… The work of protecting AI systems bears similarities to conventional computer security. Facebook’s AI red team gets its name from a term for exercises in which hackers working for an organization probe its defenses by role-playing as attackers. They know that any fixes they deploy may be side-stepped as their adversaries come up with new tricks and attacks. Read More
Rick's Cafe AI 