Chinese authorities are using a mobile app to carry out illegal mass surveillance and arbitrary detention of Muslims in China’s western Xinjiang region.
The Human Rights Watch report, “China’s Algorithms of Repression: Reverse Engineering a Xinjiang Police Mass Surveillance App,” presents new evidence about the surveillance state in Xinjiang, where the government has subjected 13 million Turkic Muslims to heightened repression as part of its “Strike Hard Campaign against Violent Terrorism.” Between January 2018 and February 2019, Human Rights Watch was able to reverse engineer the mobile app that officials use to connect to the Integrated Joint Operations Platform (IJOP), the Xinjiang policing program that aggregates data about people and flags those deemed potentially threatening. By examining the design of the app, which at the time was publicly available, Human Rights Watch revealed specifically the kinds of behaviors and people this mass surveillance system targets. Read More
Daily Archives: May 3, 2019
Facebook: New AI tech spots hate speech faster
Facebook’s AI engineers have embraced a technology called self-supervised learning so the social network’s technology can adapt faster to challenges like spotting new forms of hate speech
Artificial intelligence is sweeping the tech industry, and beyond, as the new method for getting computers to recognize patterns and make decisions catches on. With today’s AI technology called deep learning, you can get a computer to recognize a cat by training it with lots of pictures of cats, instead of figuring out how to define cat characteristics like two eyes, pointy ears and whiskers.
Self-supervised learning, though, needs vastly less training data than regular AI training, which cuts the time needed to assemble training data and train a system. For example, self-supervised learning methods have cut the amount of training data needed by a factor of 10, Manohar Paluri, an AI research leader at Facebook, said Wednesday at the company’s F8 developer conference.
And that speed is critical to making Facebook fun and safe, not a cesspool of toxic comments, misinformation, abuse and scams. Read More
Self-Supervised GANs
If you aren’t familiar with Generative Adversarial Networks (GANs), they are a massively popular generative modeling technique formed by pitting two Deep Neural Networks, a generator and a discriminator, against each other. This adversarial loss has sparked the interest of many Deep Learning and Artificial Intelligence researchers. However, despite the beauty of the GAN formulation and the eye-opening results of the state-of-the-art architectures, GANs are generally very difficult to train. One of the best ways to get better results with GANs are to provide class labels. This is the basis of the conditional-GAN model. This article will show how Self-Supervised Learning can overcome the need for class labels for training GANs and rival the performance of conditional-GAN models.
Before we get into how Self-Supervised Learning improves GANs, we will introduce the concept of Self-Supervised Learning. Compared to the popular families of Supervised and Unsupervised Learning, Self-Supervised is most similar to Unsupervised Learning. Self-Supervised tasks include things such as image colorization, predicting the relative location of extracted patches from an image, or in this case, predicting the rotation angle of an image. These tasks are dubbed “Self-Supervised” because the data lends itself to these surrogate tasks. In this sense, the Self-Supervised tasks take the form of (X, Y) pairs, however, the X,Y pairs are automatically constructed from the dataset itself and do not require human labeling. The paper discussed in this article summarizes Self-Supervised Learning as, “one can make edits to the given image and ask the network to predict the edited part”. This is the basic idea behind Self-Supervised Learning. Read More
Self-supervised learning: (Auto)encoder networks
Network must copy inputs to outputs through a “bottleneck” (fewer hidden units)
Hidden representations become a learned compressed code of the inputs/outputs
Capture systematic structure among full set of patterns Due to bottleneck, don’t have capacity to over learn idiosyncratic aspects of particular patterns
For N linear hidden units, hidden representations span the same subspace as the first N principal components (≈PCA)
Read More
Self-supervised Learning of Geometrically Stable Features Through Probabilistic Introspection
Self-supervision can dramatically cut back the amount of manually-labeled data required to train deep neural net-works. While self-supervision has usually been considered for tasks such as image classification, in this paper we aim at extending it to geometry-oriented tasks such as semantic matching and part detection. We do so by building on several recent ideas in unsupervised landmark detection. Our approach learns dense distinctive visual descriptors from an unlabeled dataset of images using synthetic image trans-formations. It does so by means of a robust probabilistic formulation that can introspectively determine which image regions are likely to result in stable image matching. We show empirically that a network pretrained in this manner requires significantly less supervision to learn semantic object parts compared to numerous pretraining alternatives.We also show that the pretrained representation is excellent for semantic object matching. Read More
Cross-Domain Self-supervised Multi-task Feature Learning using Synthetic Imagery
In human learning, it is common to use multiple sources of information jointly. However, most existing feature learning approaches learn from only a single task. In this paper,we propose a novel multi-task deep network to learn generalizable high-level visual representations. Since multi-task learning requires annotations for multiple properties of the same training instance, we look to synthetic images to train our network. To overcome the domain difference between real and synthetic data, we employ an unsupervised feature space domain adaptation method based on adversarial learning. Given an input synthetic RGB image, our network simultaneously predicts its surface normal, depth, and instance contour, while also minimizing the feature space domain differences between real and synthetic data. Through extensive experiments, we demonstrate that our network learns more transferable representations com-pared to single-task baselines. Our learned representation produces state-of-the-art transfer learning results on PAS-CAL VOC 2007 classification and 2012 detection. Read More
Exploiting Unlabeled Data in CNNs by Self-supervised Learning to Rank
For many applications the collection of labeled data is expensive laborious. Exploitation of unlabeled data during training is thus a long pursued objective of machine learning. Self-supervised learning addresses this by positing an auxiliary task (different, but related to the supervised task) for which data is abundantly available. In this paper, we show how ranking can be used as a proxy task for some regression problems. As another contribution, we propose an efficient backpropagation technique for Siamese networks which prevents the redundant computation introduced by the multi-branch network architecture.We apply our framework to two regression problems: Image Quality Assessment (IQA) and Crowd Counting. For both we show how to automatically generate ranked image sets from unlabeled data. Our results show that networks trained to regress to the ground truth targets for labeled data and to simultaneously learn to rank unlabeled data obtain significantly better, state-of-the-art results for both IQA and crowd counting. In addition, we show that measuring network uncertainty on the self-supervised proxy task is a good measure of informativeness of unlabeled data. This can be used to drive an algorithm for active learning and we show that this reduces labeling effort by up to 50%. Read More
Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey
Large-scale labeled data are generally required to train deep neural networks in order to obtain better performance in visual-feature learning from images or videos for computer vision applications. To avoid extensive cost of collecting and annotating large-scale datasets, as a subset of unsupervised learning methods, self-supervised learning methods are proposed to learn general image and video features from large-scale unlabeled data without using any human-annotated labels. This paper provides an extensive review of deep learning-based self-supervised general visual feature learning methods from images or videos. First, the motivation,general pipeline, and terminologies of this field are described. Then the common deep neural network architectures that used for self-supervised learning are summarized. Next, the schema and evaluation metrics of self-supervised learning methods are reviewed followed by the commonly used image and video datasets and the existing self-supervised visual feature learning methods. Finally,quantitative performance comparisons of the reviewed methods on benchmark datasets are summarized and discussed for both image and video feature learning. At last, this paper is concluded and lists a set of promising future directions for self-supervised visual-feature learning. Read More
Self-supervised learning gets us closer to autonomous learning
Self-Supervised Learning is getting attention because it has the potential to solve a significant limitation of supervised machine learning, viz. requiring lots of external training samples or supervisory data consisting of inputs and corresponding outputs. Yann LeCun¹ recently in a Science and Future Magazine interview presented self-supervised learning as a significant challenge of AI for the next decade.
Self-supervised learning is autonomous supervised learning. It is a representation learning approach that eliminates the pre-requisite requiring humans to label data. Self-supervised learning systems extract and use the naturally available relevant context and embedded metadata as supervisory signals. Read More
What is Self-Supervision?
A form of unsupervised learning where the data provides the supervision
In general, withhold some part of the data, and task the network with predicting it
The task defines a proxy loss, and the network is forced to learn what we really care about, e.g. a semantic representation, in order to solve it
Read More
Rick's Cafe AI 