Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userHow are attributes expressed in face DCNNs?
336
0
0.0
(
0
)
Added by
Prithviraj Dhar
Publication date
2019
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
As deep networks become increasingly accurate at recognizing faces, it is vital to understand how these networks process faces. While these networks are solely trained to recognize identities, they also contain face related information such as sex, age, and pose of the face. The networks are not trained to learn these attributes. We introduce expressivity as a measure of how much a feature vector informs us about an attribute, where a feature vector can be from internal or final layers of a network. Expressivity is computed by a second neural network whose inputs are features and attributes. The output of the second neural network approximates the mutual information between feature vectors and an attribute. We investigate the expressivity for two different deep convolutional neural network (DCNN) architectures: a Resnet-101 and an Inception Resnet v2. In the final fully connected layer of the networks, we found the order of expressivity for facial attributes to be Age > Sex > Yaw. Additionally, we studied the changes in the encoding of facial attributes over training iterations. We found that as training progresses, expressivities of yaw, sex, and age decrease. Our technique can be a tool for investigating the sources of bias in a network and a step towards explaining the networks identity decisions.
rate research
Read More
Based on a combined data set of 4000 high resolution facial scans, we introduce a non-linear morphable face model, capable of producing multifarious face geometry of pore-level resolution, coupled with material attributes for use in physically-based rendering. We aim to maximize the variety of face identities, while increasing the robustness of correspondence between unique components, including middle-frequency geometry, albedo maps, specular intensity maps and high-frequency displacement details. Our deep learning based generative model learns to correlate albedo and geometry, which ensures the anatomical correctness of the generated assets. We demonstrate potential use of our generative model for novel identity generation, model fitting, interpolation, animation, high fidelity data visualization, and low-to-high resolution data domain transferring. We hope the release of this generative model will encourage further cooperation between all graphics, vision, and data focused professionals while demonstrating the cumulative value of every individuals complete biometric profile.
Most current NLP systems have little knowledge about quantitative attributes of objects and events. We propose an unsupervised method for collecting quantitative information from large amounts of web data, and use it to create a new, very large resource consisting of distributions over physical quantities associated with objects, adjectives, and verbs which we call Distributions over Quantitative (DoQ). This contrasts with recent work in this area which has focused on making only relative comparisons such as Is a lion bigger than a wolf?. Our evaluation shows that DoQ compares favorably with state of the art results on existing datasets for relative comparisons of nouns and adjectives, and on a new dataset we introduce.
Recent studies have shown remarkable success in face image generations. However, most of the existing methods only generate face images from random noise, and cannot generate face images according to the specific attributes. In this paper, we focus on the problem of face synthesis from attributes, which aims at generating faces with specific characteristics corresponding to the given attributes. To this end, we propose a novel attributes aware face image generator method with generative adversarial networks called AFGAN. Specifically, we firstly propose a two-path embedding layer and self-attention mechanism to convert binary attribute vector to rich attribute features. Then three stacked generators generate $64 times 64$, $128 times 128$ and $256 times 256$ resolution face images respectively by taking the attribute features as input. In addition, an image-attribute matching loss is proposed to enhance the correlation between the generated images and input attributes. Extensive experiments on CelebA demonstrate the superiority of our AFGAN in terms of both qualitative and quantitative evaluations.
In the COVID-19 pandemic, among the more controversial issues is the use of face coverings. To address this we show that the underlying physics ensures particles with diameters & 1 $mu$m are efficiently filtered out by a simple cotton or surgical mask. For particles in the submicron range the efficiency depends on the material properties of the masks, though generally the filtration efficiency in this regime varies between 30 to 60 % and multi-layered cotton masks are expected to be comparable to surgical masks. Respiratory droplets are conventionally divided into coarse droplets (> 5-10 $mu$m) responsible for droplet transmission and aerosols (< 5-10 $mu$m) responsible for airborne transmission. Masks are thus expected to be highly effective at preventing droplet transmission, with their effectiveness limited only by the mask fit, compliance and appropriate usage. By contrast, knowledge of the size distribution of bioaerosols and the likelihood that they contain virus is essential to understanding their effectiveness in preventing airborne transmission. We argue from literature data on SARS-CoV-2 viral loads that the finest aerosols (< 1 $mu$m) are unlikely to contain even a single virion in the majority of cases; we thus expect masks to be effective at reducing the risk of airborne transmission in most settings.
We present a deep learning approach for high resolution face completion with multiple controllable attributes (e.g., male and smiling) under arbitrary masks. Face completion entails understanding both structural meaningfulness and appearance consistency locally and globally to fill in holes whose content do not appear elsewhere in an input image. It is a challenging task with the difficulty level increasing significantly with respect to high resolution, the complexity of holes and the controllable attributes of filled-in fragments. Our system addresses the challenges by learning a fully end-to-end framework that trains generative adversarial networks (GANs) progressively from low resolution to high resolution with conditional vectors encoding controllable attributes. We design novel network architectures to exploit information across multiple scales effectively and efficiently. We introduce new loss functions encouraging sharp completion. We show that our system can complete faces with large structural and appearance variations using a single feed-forward pass of computation with mean inference time of 0.007 seconds for images at 1024 x 1024 resolution. We also perform a pilot human study that shows our approach outperforms state-of-the-art face completion methods in terms of rank analysis. The code will be released upon publication.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
