--- title: "Why AIs Have No Idea What’s In These Mundane Pictures" description: "Researchers discovered that a new subset of 7,500 unmodified photographs of natural objects is still able to completely throw AIs for a loop." date: "2019-07-19" modified: "2019-07-19" authors: - name: "Victor Tangermann" job_title: "Senior Editor" link: "https://futurism.com/authors/victor" url: "https://futurism.com/the-byte/ai-no-idea-image-recognition" categories: - "Artificial Intelligence" tags: - "artificial intelligence" - "image recognition" - "the digest" - "vision algorithms" --- # Why AIs Have No Idea What’s In These Mundane Pictures ![A new subset of 7,500 unmodified photographs of natural objects is still able to completely throw AIs for a loop.]() *\Image: Hendrycks et al./Victor Tangermann\* ## Wrong Again Image recognition software powered by artificial intelligence has come a long way. But it's not foolproof: a team of researchers found that about two percent of the time, machine vision systems will have no idea what they're looking at, even if it's blatantly obvious to a human. The researchers discovered 7,500 unmodified photographs of objects that are able to completely throw AIs for a loop. A [preprint]() of their research was published in the repository arXiv. ![]() Thanks to "deep flaws in current classifiers including their over-reliance on color, texture, background cues," the accuracy of an AI drops dramatically. The result: an image of a lynx gets classified as a crayfish or an alligator gets confused with a hummingbird. ## ImageNet The photos belong to a much larger industry-standard database called ImageNet — comprised of millions of hand-labeled images — that often gets used to train image recognition AIs. The database was first put together in 2006 and over the years, AI models have become more and more accurate at predicting what they see in the millions of photos. But AI-powered image recognition systems are still far from perfect. For instance in 2018, Amazon's face recognition AI called Rekognition [incorrectly matched]() 28 members of Congress with mugshots of criminals. The researchers are hopeful their research will eventually lead to more accurate and robust machine vision systems that are able to additionally consider the context of the image, not just the image itself. **READ MORE:** [AI fails to recognize these nature images 98% of the time]() \[*The Next Web*\] **More on machine vision:** *[Scientists Create an AI From a Sheet of Glass]()* ## Author I've been at Futurism since 2017, where my role has evolved to encompass design, writing, and increasingly editing. I've always been fascinated by space exploration and advanced transportation, which I've leaned into by interviewing luminaries in those fields while closely following the dimensions of policy and regulation that allow next-generation projects to succeed -- or, sometimes, to fail. I'm also keenly interested in the effects of generative AI on society, policies, and democratic institutions, as well as clean energy, physics and biology, and the vagaries of tech leadership. My work for Futurism has been cited by publications including Ars Technica, Gizmodo, PC Magazine, Jalopnik, Fox News, and the New York Post. I spent my childhood living in locations including Manila, the Philippines, and Geneva, Switzerland, attended McGill University, and now live in Toronto, Canada. Before Futurism I worked at AskMen and a small photography studio. In my free time, I'm an avid gardener, foodie, and craft beer lover, as well as a maker of artisanal hot pepper sauces. I have a magnificent dog named Freida. ### Author social links [Bluesky]()