State-of-the-art image and text classification models, such as Convolutional Neural Networks and Transformers, have long been able to classify their respective unimodal reasoning satisfactorily with accuracy close to or exceeding human accuracy. However, images embedded with text, such as hateful memes, are hard to classify using unimodal reasoning when difficult examples, such as benign confounders, are incorporated into the data set. We attempt to generate more labeled memes in addition to the Hateful Memes data set from Facebook AI, based on the framework of a winning team from the Hateful Meme Challenge. To increase the number of labeled memes, we explore semi-supervised learning using pseudo-labels for newly introduced, unlabeled memes gathered from the Memotion Dataset 7K. We find that the semi-supervised learning task on unlabeled data required human intervention and filtering and that adding a limited amount of new data yields no extra classification performance.

Artificial Intelligence, or AI, is an ever-evolving field. And the occasional failures here and there should not stop us from hyping the great advancements. In the last year and half, despite the global crisis– in some cases, because of the global crisis– scientists, researchers and developers have made insane contributions, innovated and have reached unprecedented milestones in the field of AI. As we head closer to the end of 2021, Analytics India Magazine takes a look back at the year that was, and the AI innovations and milestones of this year that made it to the headlines. Early this year Facebook AI developed SEER (SElf-supERvised)– a billion-parameter self-supervised computer vision model.

Meta CEO Mark Zuckerberg announced Monday that the company has designed a new synthetic skin for robots that could enable the machines to help build the company's metaverse. A development collaboration with Carnegie Mellon University, ReSkin lets robots'feel' objects to know how much or little force should be used to perform tasks, such as gripping or moving small objects. The skin is up to three millimeters thick and can be used for more than 50,000 interactions, while also having a high temporal resolution of up to 400Hz and a spatial resolution of one millimeter with 90 percent accuracy. ReSkin is also inexpensive to produce, costing less than $6 each at 100 units and even less at larger quantities, Facebook AI shared in a blog post. Abhinav Gupta, a research scientist at Meta, said on a media call Friday robots that can feel will help the machines understand what humans are doing.

The Old Testament's'Tower of Babel' story is an origin myth that tries to explain why humanity doesn't speak a single, universal language. According to the Bible, a united human race that speaks the same language arrived in the land of Shinar and decided to build a tower tall enough to reach heaven. Annoyed -- once again, it can probably be said -- by humanity's growing arrogance and budding hubris, God confounded humanity's speech, dividing its people into separate linguistic groups that couldn't understand one another. Just to ensure they don't start comparing and contrasting their languages to reach some form of translating breakthrough, God dispersed humankind to all corners of the earth and set the stage for what is today a world of 6,500 languages. For God, a job well done and the situation remained static for centuries, that was until tribes starting trading with each other, armies started fighting one another, and diplomats initiated conflict resolution measures to try to end the wars that were often started due to misunderstandings of one kind or another.

AI that understands the world from a first-person point of view could unlock a new era of immersive experiences, as devices like augmented reality (AR) glasses and virtual reality (VR) headsets become as useful in everyday life as smartphones. Imagine your AR device displaying exactly how to hold the sticks during a drum lesson, guiding you through a recipe, helping you find your lost keys, or recalling memories as holograms that come to life in front of you. To build these new technologies, we need to teach AI to understand and interact with the world like we do, from a first-person perspective -- commonly referred to in the research community as egocentric perception. Today's computer vision (CV) systems, however, typically learn from millions of photos and videos that are captured in third-person perspective, where the camera is just a spectator to the action. "Next-generation AI systems will need to learn from an entirely different kind of data -- videos that show the world from the center of the action, rather than the sidelines," says Kristen Grauman, lead research scientist at Facebook.

Researchers at Carnegie Mellon University helped compile and will have access to the largest collection of point-of-view videos in the world. These videos could enable artificial intelligence to understand the world from a first-person point of view and unlock a new wave of virtual assistants, augmented reality and robotics. Until now, most of the video used to train computer vision models came from the third-person point of view. The first-person, or egocentric, video included in this collection will allow researchers to train computer vision systems to see the world as humans do. "For the first time, we'll have enough data to be able to teach computers to see what we see," said Kris Kitani, an associate research professor in the Robotics Institute who led CMU's efforts to collect data.

I've always found the fact that the acronym for artificial intelligence in English, AI, is surprisingly similar to the first two characters for that word in both simplified Chinese -- '人工智能'. The first two characters together, 人工, mean'people' and'work' individually, but when put together mean'artificial' while '智能' means'intelligent.' This is quite a fascinating linguistic experiment, and it's interesting that the two most widely used languages in the world came up a similar acronym or character for one of the most important technologies ever invented by man. Perhaps there is some weird universal synergy going on or maybe there's an easy answer hidden somewhere deep within the linguistic annals of these two languages. Either way, this got me thinking about language.

Robots can be designed to clean the floor, as long as everything they might encounter in the room has a programmed response. Suddenly introduce an open bottle of juice and the robot is likely to knock it over then smear juice all over the floor, completely unaware that it is making the situation worse. Robots can be designed to answer questions from humans, as long as every question has a programmed response – ask something new and the robot will have very little to say. Robots can even be designed to dance, but try to dance with it and we are likely to get hurt as the robot cannot read and react to our unpredictable human dance moves. This is the stage robotics is at today, but recent developments in artificial intelligence (AI) may now open the door to robots that can whirl you round the dancefloor, charm you with natural conversation, and even clean up the unpredictable mess afterwards.

Last April, Facebook's AI research lab (FAIR) announced and released as open source its BlenderBot social chat app. While the neophyte AI immediately proved far less prone to racist outbursts than previous attempts, BlenderBot was not without its shortcomings. For one, the system had the recollection capacity of a goldfish -- any subject or data point the AI wasn't initially trained simply didn't exist in its online reality, as evidenced by the OG BB's continued insistence that Tom Brady still plays for the New England Patriots. For another, due to its limited knowledge of current events, the system had a strong tendency to hallucinate knowledge, like a digital Dunning-Kruger effect. But the advancements BlenderBot 2.0 displays, which FAIR debuted on Friday, should make the AI far more sociable, knowledgeable, and capable.

We also worked with trained third-party annotators to manually transform a smaller subset of the images to ensure we have even more selections representative of the way a human user would transform images. The annotators used image manipulation software GIMP to manually alter images in diverse ways that we cannot easily automate, for example handwriting or drawing on the images or cropping to leave only the part of the image most salient to the human eye. The Image Similarity Challenge invites participants to test their image matching techniques on the Image Similarity data set. More information for researchers is available here, and the accompanying paper is available here. For researchers considering attending NeurIPS 2021 in December, we're also pleased to announce that the Image Similarity Challenge has been accepted for the NeurIPS 2021 competition track, where we will be announcing the winners of this challenge (The competition is subject to official rules.