Search Results for author:
Found 31 papers, 6 papers with code
Watchlist Challenge: 3rd Open-set Face Detection and Identification
In the current landscape of biometrics and surveillance, the ability to accurately recognize faces in uncontrolled settings is paramount.
Open-Set Face Recognition with Maximal Entropy and Objectosphere Loss
MEL modifies the traditional Cross-Entropy loss in favor of increasing the entropy for negative samples and attaches a penalty to known target classes in pursuance of gallery specialization.
Large-scale Fully-Unsupervised Re-Identification
Fully-unsupervised Person and Vehicle Re-Identification have received increasing attention due to their broad applicability in surveillance, forensics, event understanding, and smart cities, without requiring any manual annotation.
DaliID: Distortion-Adaptive Learned Invariance for Identification Models
In unconstrained scenarios, face recognition and person re-identification are subject to distortions such as motion blur, atmospheric turbulence, or upsampling artifacts.
Enhanced Performance of Pre-Trained Networks by Matched Augmentation Distributions
Specifically, we demonstrate that running inference on the center crop of an image is not always the best as important discriminatory information may be cropped-off.
Self-Supervised Features Improve Open-World Learning
This paper identifies the flaws in existing open-world learning approaches and attempts to provide a complete picture in the form of \textbf{True Open-World Learning}.
A Review of Open-World Learning and Steps Toward Open-World Learning Without Labels
Open-world learning is related to but also distinct from a multitude of other learning problems and this paper briefly analyzes the key differences between a wide range of problems including incremental learning, generalized novelty discovery, and generalized zero-shot learning.
Automatic Open-World Reliability Assessment
However, during operations, we cannot directly assess accuracy as there are no labels.
Adversarial Attack on Deep Learning-Based Splice Localization
Regarding image forensics, researchers have proposed various approaches to detect and/or localize manipulations, such as splices.
To Beta or Not To Beta: Information Bottleneck for DigitaL Image Forensics
We propose an innovative method to formulate the issue of localizing manipulated regions in an image as a deep representation learning problem using the Information Bottleneck (IB), which has recently gained popularity as a framework for interpreting deep neural networks.
Improved Adversarial Robustness by Reducing Open Space Risk via Tent Activations
On the CIFAR-10 dataset, our approach improves the average accuracy against the six white-box adversarial attacks to 73. 5% from 41. 8% achieved by adversarial training via PGD.
SpliceRadar: A Learned Method For Blind Image Forensics
It comprises a novel approach for learning rich filters and for suppressing image-edges.
Reducing Network Agnostophobia
Agnostophobia, the fear of the unknown, can be experienced by deep learning engineers while applying their networks to real-world applications.
Facial Attributes: Accuracy and Adversarial Robustness
Facial attributes, emerging soft biometrics, must be automatically and reliably extracted from images in order to be usable in stand-alone systems.
The Unconstrained Ear Recognition Challenge
In this paper we present the results of the Unconstrained Ear Recognition Challenge (UERC), a group benchmarking effort centered around the problem of person recognition from ear images captured in uncontrolled conditions.
Unconstrained Face Detection and Open-Set Face Recognition Challenge
Face detection and recognition benchmarks have shifted toward more difficult environments.
Adversarial Robustness: Softmax versus Openmax
Deep neural networks (DNNs) provide state-of-the-art results on various tasks and are widely used in real world applications.
Toward Open-Set Face Recognition
In this paper, we address the widespread misconception that thresholding verification-like scores is a good way to solve the open-set face identification problem, by formulating an open-set face identification protocol and evaluating different strategies for assessing similarity.
Towards Robust Deep Neural Networks with BANG
Machine learning models, including state-of-the-art deep neural networks, are vulnerable to small perturbations that cause unexpected classification errors.
LOTS about Attacking Deep Features
We demonstrate that iterative LOTS is very effective and show that systems utilizing deep features are easier to attack than the end-to-end network.
AFFACT - Alignment-Free Facial Attribute Classification Technique
Using an ensemble of three ResNets, we obtain the new state-of-the-art facial attribute classification error of 8. 00% on the aligned images of the CelebA dataset.
Automated Big Text Security Classification
To analyze the ACESS system, we constructed a novel dataset, containing formerly classified paragraphs from diplomatic cables made public by the WikiLeaks organization.
Are Accuracy and Robustness Correlated?
In this paper, we perform experiments on various adversarial example generation approaches with multiple deep convolutional neural networks including Residual Networks, the best performing models on ImageNet Large-Scale Visual Recognition Challenge 2015.
Assessing Threat of Adversarial Examples on Deep Neural Networks
Deep neural networks are facing a potential security threat from adversarial examples, inputs that look normal but cause an incorrect classification by the deep neural network.
Specialized Support Vector Machines for Open-set Recognition
In the open-set scenario, however, a test sample can belong to none of the known classes and the classifier must properly reject it by classifying it as unknown.
Are Facial Attributes Adversarially Robust?
We show that FFA generates more adversarial examples than other related algorithms, and that DCNNs for certain attributes are generally robust to adversarial inputs, while DCNNs for other attributes are not.
PARAPH: Presentation Attack Rejection by Analyzing Polarization Hypotheses
Thus, there is great demand for an effective and low cost system capable of rejecting such attacks. To this end we introduce PARAPH -- a novel hardware extension that exploits different measurements of light polarization to yield an image space in which presentation media are readily discernible from Bona Fide facial characteristics.
Adversarial Diversity and Hard Positive Generation
Finally, we demonstrate on LeNet and GoogLeNet that fine-tuning with a diverse set of hard positives improves the robustness of these networks compared to training with prior methods of generating adversarial images.
A Survey of Stealth Malware: Attacks, Mitigation Measures, and Steps Toward Autonomous Open World Solutions
While machine learning offers promising potential for increasingly autonomous solutions with improved generalization to new malware types, both at the network level and at the host level, our findings suggest that several flawed assumptions inherent to most recognition algorithms prevent a direct mapping between the stealth malware recognition problem and a machine learning solution.
The Extreme Value Machine
It is often desirable to be able to recognize when inputs to a recognition function learned in a supervised manner correspond to classes unseen at training time.
Pruning Bayesian Networks for Efficient Computation
We define a computationally equivalent subgraph of a Bayesian network.
