Deep-learning-based methods for different applications have been shown vulnerable to adversarial examples. These examples make deployment of such models in safety-critical tasks questionable.Use of deep neural networks as inverse problem solvers has generated much excitement for medical imaging including CT and MRI, but recently a similar vulnerability has also been demonstrated for these tasks. We show that for such inverse problem solvers, one should analyze and study the effect of adversaries in the measurement-space,instead of the signal-space as in previous work. Read More
Tag Archives: Image Recognition
Dense Steerable Filter CNNs for Exploiting Rotational Symmetry in Histology Images
Histology images are inherently symmetric under rotation, where each orientation is equally as likely to appear. However, this rotational symmetry is not widely utilised as prior knowledge in modern Convolutional Neural Networks (CNNs),resulting in data hungry models that learn independent features at each orientation. Allowing CNNs to be rotation-equivariant removes the necessity to learn this set of transformations from the data and instead frees up model capacity, allowing more discriminative features to be learned. This reduction in the number of required parameters also reduces the risk of over-fitting. In this paper, we propose Dense Steerable Filter CNNs (DSF-CNNs) that use group convolutions with multiple rotated copies of each filter in a densely connected framework. Each filter is defined as a linear combination of steerable basis filters,enabling exact rotation and decreasing the number of trainable parameters compared to standard filters. We also provide the first in-depth comparison of different rotation-equivariant CNNs for histology image analysis and demonstrate the advantage of encoding rotational symmetry into modern architectures. We show that DSF-CNNs achieve state-of-the-art performance, with significantly fewer parameters, when applied to three different tasks in the area of computational pathology: breast tumour classification, colon gland segmentation and multi-tissue nuclear segmentation. Read More
End-to-End Object Detection with Transformers
We present a new method that views object detection as a direct set prediction problem. Our approach streamlines the detection pipeline, effectively removing the need for many hand-designed components like a non-maximum suppression procedure or anchor generation that explicitly encode our prior knowledge about the task. The main ingredients of the new framework, called DEtection TRansformer or DETR, are a set-based global loss that forces unique predictions via bipartite matching, and a transformer encoder-decoder architecture. Given a fixed small set of learned object queries, DETR reasons about the relations of the objects and the global image context to directly output the final set of predictions in parallel. The new model is conceptually simple and does not require a specialized library, unlike many other modern detectors. DETR demonstrates accuracy and run-time performance on par with the well-established and highly-optimized Faster R-CNN baseline on the challenging COCO object detection dataset. More-over, DETR can be easily generalized to produce panoptic segmentation in a unified manner. We show that it significantly outperforms competitive baselines. Read More
Why it matters that IBM is getting out of the facial recognition business
The news that IBM will no longer produce facial recognition technology might not sound huge at first. The company’s commitment to opposing this type of racially biased surveillance technology fits into a welcome trend of actions being taken after anti-police brutality protests have swept the nation. Although some are already warning that IBM’s move won’t end the age of facial recognition, others say it’s a significant step in the right direction. Read More
AI RT Artist uses AI to create realistic-looking portraits of famous figures including Napoleon and Van Gogh
AN ARTIST has used artificial intelligence to create human-like portraits from statues and paintings of famous faces.
If you’ve ever wondered whatthe Statue of Liberty or Michelangelo’s David statue would look like as real people then take a look. Read More
For AI, data are harder to come by than you think
AMAZON’S “GO” STORES are impressive places. The cashier-less shops, which first opened in Seattle in 2018, allow app-wielding customers to pick up items and simply walk out with them. The system uses many sensors, but the bulk of the magic is performed by cameras connected to an AI system that tracks items as they are taken from shelves. Once the shoppers leave with their goods, the bill is calculated and they are automatically charged. Read More
Turning any CNN image classifier into an object detector with Keras, TensorFlow, and OpenCV
In this tutorial, you will learn how to take any pre-trained deep learning image classifier and turn it into an object detector using Keras, TensorFlow, and OpenCV.
Today, we’re starting a four-part series on deep learning and object detection:
- Part 1: Turning any deep learning image classifier into an object detector with Keras and TensorFlow (today’s post)
- Part 2: OpenCV Selective Search for Object Detection
- Part 3: Region proposal for object detection with OpenCV, Keras, and TensorFlow
- Part 4: R-CNN object detection with Keras and TensorFlow
Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wild
We propose a method to learn 3D deformable object categories from raw single-view images, without external supervision. The method is based on an autoencoder that factors each input image into depth, albedo, viewpoint and illumination. In order to disentangle these components without supervision, we use the fact that many object categories have, at least in principle, a symmetric structure. We show that reasoning about illumination allows us to exploit the underlying object symmetry even if the appearance is not symmetric due to shading. Furthermore, we model objects that are probably, but not certainly, symmetric by predicting a symmetry probability map, learned end-to-end with the other components of the model. Our experiments show that this method can recover very accurately the 3D shape of human faces, cat faces and cars from single-view images, without any supervision or a prior shape model. On benchmarks, we demonstrate superior accuracy compared to another method that uses supervision at the level of 2D image correspondences. Read More
#human, #image-recognitionHas Media & Entertainment Cracked the AI Code?
Artificial Intelligence (AI) and Machine Learning (ML) are technologies that enterprises across industries have been keenly experimenting with to explore the utility they can bring. Is there AI adoption within the M&E industry? Can AI be the solution for enterprises seeking automation? Have we cracked the AI code or do we have miles to go? If automation is a goal, it should be a priority even now.
Content recommendation (for OTT), speech-to-text and media recognition are some of the initial applications that have been attempted. Clients find vendor demos to be impressive, but when they do a proof of concept (PoC) with their content, results are not. In video operations, frame accuracy is a necessity and AI models struggle to universally solve for this. And such specific nuances of getting it right, is what makes automation work. After trying multiple vendors, clients conclude that AI data is still not accurate enough to solve specific M&E use cases. However, they remain optimistic about the future possibilities.
So where is the issue? Read More
PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization∗
Recent advances in image-based 3D human shape estimation have been driven by the significant improvement in representation power afforded by deep neural networks.Although current approaches have demonstrated the potential in real world settings, they still fail to produce reconstructions with the level of detail often present in the input images. We argue that this limitation stems primarily form two conflicting requirements; accurate predictions require large context, but precise predictions require high resolution. Due to memory limitations in current hardware,previous approaches tend to take low resolution images asinput to cover large spatial context, and produce less precise(or low resolution) 3D estimates as a result. We address this limitation by formulating a multi-level architecture that is end-to-end trainable. A coarse level observes the whole image at lower resolution and focuses on holistic reasoning.This provides context to an fine level which estimates highly detailed geometry by observing higher-resolution images.We demonstrate that our approach significantly outperforms existing state-of-the-art techniques on single image human shape reconstruction by fully leveraging 1k-resolution input images. Read More
Rick's Cafe AI 