Companies are using bizarre methods to create algorithms that automatically detect weapons. AI ethicists worry they will lead to more police violence.
In Huntsville, Alabama, there is a room with green walls and a green ceiling. Dangling down the center is a fishing line attached to a motor mounted to the ceiling, which moves a procession of guns tied to the translucent line.
The staff at Arcarithm bought each of the 10 best-selling firearm models in the U.S.: Rugers, Glocks, Sig Sauers. Pistols and long guns are dangled from the line. The motor rotates them around the room, helping a camera mounted to a mobile platform photograph them from multiple angles. “ Read More
Tag Archives: Image Recognition
Learning Transferable Visual Models From Natural Language Supervision
State-of-the-art computer vision systems are trained to predict a fixed set of predetermined object categories. This restricted form of super-vision limits their generality and usability since additional labeled data is needed to specify any other visual concept. Learning directly from raw text about images is a promising alternative which leverages a much broader source of supervision.We demonstrate that the simple pretraining task of predicting which caption goes with which image is an efficient and scalable way to learn SOTA image representations from scratch on a dataset of 400 million (image, text) pairs collected from the internet. After pretraining, natural language is used to reference learned visual concepts (or describe new ones) enabling zero-shot transfer of the model to downstream tasks. We study the performance of this approach by benchmarking on over 30 different existing computer vision datasets, spanning tasks such as OCR, action recognition in videos, geo-localization, and many types of fine-grained object classification. The model transfers non-trivially to most tasks and is often competitive with a fully supervised baseline without the need for any dataset specific training.For instance, we match the accuracy of the original ResNet-50 on ImageNet zero-shot without needing to use any of the 1.28 million training examples it was trained on. Read More
#image-recognition, #nlpFacial recognition technology can expose political orientation from naturalistic facial images
Ubiquitous facial recognition technology can expose individuals’ political orientation, as faces of liberals and conservatives consistently differ. A facial recognition algorithm was applied to naturalistic images of 1,085,795 individuals to predict their political orientation by comparing their similarity to faces of liberal and conservative others. Political orientation was correctly classified in 72% of liberal–conservative face pairs, remarkably better than chance (50%), human accuracy (55%), or one afforded by a 100-item personality questionnaire (66%). Accuracy was similar across countries (the U.S., Canada, and the UK), environments (Facebook and dating websites), and when comparing faces across samples. Accuracy remained high (69%) even when controlling for age, gender, and ethnicity. Given the widespread use of facial recognition, our findings have critical implications for the protection of privacy and civil liberties. Read More
High-Quality Background Removal Without Green Screens
Human matting is an extremely interesting task where the goal is to find any human in a picture and remove the background from it. It is really hard to achieve due to the complexity of the task, having to find the person or people with the perfect contour. … The MODNet background removal technique can extract a person from a single input image, without the need for a green screen in real-time! Read More
Open AI CLIP: learning visual concepts from natural language supervision
A few days ago OpenAI released 2 impressive models CLIP and DALL-E. While DALL-E is able to generate text from images, CLIP classifies a very wide range of images by turning image classification into a text similarity problem. The issue with current image classification networks is that they are trained on a fixed number of categories, CLIP doesn’t work this way, it learns directly from the raw text about images, and thus it isn’t limited by labels and supervision. This is quite impressive, CLIP can classify images with state of the art accuracy without any dataset-specific training. Read More
Bird by Bird using Deep Learning
This article demonstrates how deep learning models used for image-related tasks can be advanced in order to address the fine-grained classification problem. For this objective, we will walk through the following two parts. First, you will get familiar with some basic concepts of computer vision and convolutional neural networks, while the second part demonstrates how to apply this knowledge to a real-world problem of bird species classification using PyTorch. Specifically, you will learn how to build your own CNN model – ResNet-50, – to further improve its performance using transfer learning, auxiliary task and attention-enhanced architecture, and even a little more. Read More
Adaptive Discriminator Augmentation: GAN Training Breakthrough for Limited Data Applications
Neuroscientists find a way to make object-recognition models perform better
Computer vision models known as convolutional neural networks can be trained to recognize objects nearly as accurately as humans do. However, these models have one significant flaw: Very small changes to an image, which would be nearly imperceptible to a human viewer, can trick them into making egregious errors such as classifying a cat as a tree.
A team of neuroscientists from MIT, Harvard University, and IBM have developed a way to alleviate this vulnerability, by adding to these models a new layer that is designed to mimic the earliest stage of the brain’s visual processing system. In a new study, they showed that this layer greatly improved the models’ robustness against this type of mistake. Read More
Contrastive Learning of Medical Visual Representations from Paired Images and Text
Learning visual representations of medical images is core to medical image understanding but its progress has been held back by the small size of hand-labeled datasets. Existing work commonly relies on transferring weights from ImageNet pretraining, which is suboptimal due to drastically different image characteristics,or rule-based label extraction from the textual report data paired with medical images, which is inaccurate and hard to generalize. We propose an alternative unsupervised strategy to learn medical visual representations directly from the naturally occurring pairing of images and textual data. Our method of pretraining medical image encoders with the paired text data via a bidirectional contrastive objective between the two modalities is domain-agnostic, and requires no additional expert input. We test our method by transferring our pretrained weights to 4 medical image classification tasks and 2 zero-shot retrieval tasks, and show that our method leads to image representations that considerably outperform strong base-lines in most settings. Notably, in all 4 classification tasks, our method requires only 10% as much labeled training data as an ImageNet initialized counterpart to achieve better or comparable performance, demonstrating superior data efficiency. Read More
Guide to Visual Recognition Datasets for Deep Learning with Python Code
Some visual recognition datasets have set benchmarks for supervised learning (Caltech101, Caltech256, CaltechBirds, CIFAR-10 andCIFAR-100) and unsupervised or self-taught learning algorithms(STL10) using deep learning across different object categories for various researches and developments. Under visual recognition mainly comes image classification, image segmentation and localization, object detection and various other use case problems. Many of these datasets have APIs present across some deep learning frameworks. This article talks about some of these datasets features along with some python code snippets on how to use them. Read More
Rick's Cafe AI 