Evaluations of large-scale recognition methods typically focus on overall performance. While this approach is common, it often fails to provide insights into performance across individual classes, which can lead to fairness issues and misrepresentation. Addressing these gaps is crucial for accurately assessing how well methods handle novel or unseen classes and ensuring a fair evaluation. To address fairness in Open-Set Recognition (OSR), we demonstrate that per-class performance can vary dramatically. We introduce Gaussian Hypothesis Open Set Technique (GHOST), a novel hyperparameter-free algorithm that models deep features using class-wise multivariate Gaussian distributions with diagonal covariance matrices. We apply Z-score normalization to logits to mitigate the impact of feature magnitudes that deviate from the model’s expectations, thereby reducing the likelihood of the network assigning a high score to an unknown sample. We evaluate GHOST across multiple ImageNet-1K pre-trained deep networks and test it with four different unknown datasets. Using standard metrics such as AUOSCR, AUROC and FPR95, we achieve statistically significant improvements, advancing the state-of-the-art in large-scale OSR. Source code is provided online.

In the current landscape of biometrics and surveillance, the ability to accurately recognize faces in uncontrolled settings is paramount. The Watchlist Challenge addresses this critical need by focusing on face detection and open-set identification in real-world surveillance scenarios. This paper presents a comprehensive evaluation of participating algorithms, using the enhanced UnConstrained College Students (UCCS) dataset with new evaluation protocols. In total, four participants submitted four face detection and nine open-set face recognition systems. The evaluation demonstrates that while detection capabilities are generally robust, closed-set identification performance varies significantly, with models pre-trained on large-scale datasets showing superior performance. However, open-set scenarios require further improvement, especially at higher true positive identification rates, i.e., lower thresholds.

Fair biometric algorithms have similar verification performance across different demographic groups given a single decision threshold. Unfortunately, for stateof-the-art face recognition networks, score distributions differ between demographics. Contrary to work that tries to align those distributions by extra training or fine-tuning, we solely focus on score post-processing methods. As proved, well-known sample-centered score normalization techniques, Z-norm and T-norm, do not improve fairness for high-security operating points. Thus, we extend the standard Z/T-norm to integrate demographic information in normalization. Additionally, we investigate several possibilities to incorporate cohort similarities for both genuine and impostor pairs per demographic to improve fairness across different operating points. We run experiments on two datasets with different demographics (gender and ethnicity) and show that our techniques generally improve the overall fairness of five state-of-the-art pre-trained face recognition networks, without downgrading verification performance. We also indicate that an equal contribution of False Match Rate (FMR) and False Non-Match Rate (FNMR) in fairness evaluation is required for the highest gains. Code and protocols are available.‡‡

Face recognition in the wild has gained a lot of focus in the last few years, and many face recognition models are designed to verify faces in medium-quality images. Especially due to the availability of large training datasets with similar conditions, deep face recognition models perform exceptionally well in such tasks. However, in other tasks where substantially less training data is available, such methods struggle, especially when required to compare high-quality enrollment images with low-quality probes. On the other hand, traditional RankList-based methods have been developed that compare faces indirectly by comparing to cohort faces with similar conditions. In this paper, we revisit these RankList methods and extend them to use the logits of the state-of-the-art DaliFace network, instead of an external cohort. We show that through a reasonable Logit-Cohort Selection (LoCoS) the performance of RankList-based functions can be improved drastically. Experiments on two challenging face recognition datasets not only demonstrate the enhanced performance of our proposed method but also set the stage for future advancements in handling diverse image qualities.

As researchers strive to narrow the gap between machine intelligence and human through the development of artificial intelligence multimedia technologies, it is imperative that we recognize the critical importance of trustworthiness in open-world, which has become ubiquitous in all aspects of daily life for everyone. However, several challenges may create a crisis of trust in current open-world artificial multimedia systems that need to be bridged: 1) Insufficient explanation of predictive results; 2) Inadequate generalization for learning models; 3) Poor adaptability to uncertain environments. Consequently, we explore a neural program to bridge trustworthiness and open-world learning, extending from single-modal to multi-modal scenarios for readers.1) To enhance design-level interpretability, we first customize trustworthy networks with specific physical meanings; 2) We then design environmental well-being task-interfaces via flexible learning regularizers for improving the generalization of trustworthy learning; 3) We propose to increase the robustness of trustworthy learning by integrating open-world recognition losses with agent mechanisms. Eventually, we enhance various trustworthy properties through the establishment of design-level explainability, environmental well-being task-interfaces and open-world recognition programs. As a result, these designed open-world protocols are applicable across a wide range of surroundings, under open-world multimedia recognition scenarios with significant performance improvements observed.

Open-Set Classification (OSC) intends to adapt closed-set classification models to real-world scenarios, where the classifier must correctly label samples of known classes while rejecting previously unseen unknown samples. Only recently, research started to investigate on algorithms that are able to handle these unknown samples correctly. Some of these approaches address OSC by including into the training set negative samples that a classifier learns to reject, expecting that these data increase the robustness of the classifier on unknown classes. Most of these approaches are evaluated on small-scale and low-resolution image datasets like MNIST, SVHN or CIFAR, which makes it difficult to assess their applicability to the real world, and to compare them among each other. We propose three open-set protocols that provide rich datasets of natural images with different levels of similarity between known and unknown classes. The protocols consist of subsets of ImageNet classes selected to provide training and testing data closer to real-world scenarios. Additionally, we propose a new validation metric that can be employed to assess whether the training of deep learning models addresses both the classification of known samples and the rejection of unknown samples. We use the protocols to compare the performance of two baseline open-set algorithms to the standard SoftMax baseline and find that the algorithms work well on negative samples that have been seen during training, and partially on out-of-distribution detection tasks, but drop performance in the presence of samples from previously unseen unknown classes.

Clustering has a long history in the computer vision community with a myriad of applications. Clustering is a family of unsupervised machine learning techniques that group samples based on similarity. Multiple ad hoc techniques have been developed to combine or fuse clustering algorithms with dozens of different clustering techniques. This paper presents a new formalization of clustering fusion and introduces the novel Commonality Fusion (ComFu) technique to combine the advantages of different clustering algorithms by fusing their results on datasets. ComFu builds a pairwise commonality matrix of samples by computing how many clustering algorithms group each pair together. Using this matrix, ComFu builds initial clusters of points with high commonality and then assigns points with low commonality to clusters with the highest average commonality to those points with an automatic distance measure selection process. We start experiments by comparing ComFu with the prior state-of-the-art cluster fusion algorithms on eight UCI datasets. We then evaluate ComFu on practical vision clustering problems, advancing the state-of-the-art on a wide range of applications including clustering faces in the IJB-B dataset. We apply ComFu to fuse FINCH, the state-of-the-art ”parameter-free” approach, which returns multiple partitions and can use multiple distance metrics, and show that ComFu improves their result by fusing over metrics and partitions.

In real-world deployments, machine learning applications find challenges when accessing ever-increasing volumes of data - the real world is open and often presents data from classes not seen in training. Open-set recognition is a growing area of machine learning addressing such problems. This research work advances the state-of-the-art in open-set recognition, the Extreme Value Machine (EVM), with a novel clustering-based extension (C-EVM) during training to improve the end-to-end prediction performance. The C-EVM combines Density-based spatial clustering of applications with noise (DBSCAN)-based clustering with a novel Nearby Clusters (NC) algorithm during model fitting to reduce computation while improving accuracy. Our experiments show a statistically significant improvement of 5-10% in macro F1-score over the state-of-the-art EVM on open-set testing using the KDD CUP-99 data set. Past work on open set recognition often traded improved open-set robustness for a decrease in closed-set accuracy, whereas C-EVM outperforms the EVM in both closed-set and open-set recognition. Testing on subsets of ImageNet-2012 with varying numbers of classes, the C-EVM statistically significantly out performs EVM when using deep features. A parameterless Hierarchical DBSCAN (HDBSCAN)-based C-EVM variant is introduced as part of this work that scales well for large data sets. Finally, both EVM and C-EVM can operate as kernel-free incremental learners, enabling these open-set multi-class classifiers to be useful for streaming and big data applications.

Even though object detection is a popular area of research that has found considerable applications in the real world, it has some fundamental aspects that have never been formally discussed and experimented. One of the core aspects of evaluating object detectors has been the ability to avoid false detections. While major datasets like PASCAL VOC or MSCOCO extensively test the detectors on their ability to avoid false positives, they do not differentiate between their closed-set and open-set performance. Despite systems being trained to reject everything other than the classes of interest, unknown objects from the open world end up being incorrectly detected as known objects, often with very high confidence. This paper is the first to formalize the problem of open-set object detection and propose the first open-set object detection protocol. Moreover, the paper provides a new evaluation metric to analyze the performance of some state-of-the-art detectors and discusses their performance differences.

As science attempts to close the gap between man and machine by building systems capable of learning, we must embrace the importance of the unknown. The ability to differentiate between known and unknown can be considered a critical element of any intelligent self-learning system. The ability to reject uncertain inputs has a very long history in machine learning, as does including a background or garbage class to account for inputs that are not of interest. This paper explains why neither of these is genuinely sufficient for handling unknown inputs – uncertain is not unknown, and unknowns need not appear to be uncertain to a learning system. The past decade has seen the formalization and development of many open set algorithms, which provably bound the risk from unknown classes. We summarize the state of the art, core ideas, and results and explain why, despite the efforts to date, the current techniques are genuinely insufficient for handling unknown inputs, especially for deep networks.

Agnostophobia, the fear of the unknown, can be experienced by deep learning engineers while applying their networks to real-world applications. Unfortunately, network behavior is not well defined for inputs far from a networks training set. In an uncontrolled environment, networks face many instances that are not of interest to them and have to be rejected in order to avoid a false positive. This problem has previously been tackled by researchers by either a) thresholding softmax, which by construction cannot return "none of the known classes", or b) using an additional background or garbage class. In this paper, we show that both of these approaches help, but are generally insufficient when previously unseen classes are encountered. We also introduce a new evaluation metric that focuses on comparing the performance of multiple approaches in scenarios where such unseen classes or unknowns are encountered. Our major contributions are simple yet effective Entropic Open-Set and Objectosphere losses that train networks using negative samples from some classes. These novel losses are designed to maximize entropy for unknown inputs while increasing separation in deep feature space by modifying magnitudes of known and unknown samples. Experiments on networks trained to classify classes from MNIST and CIFAR-10 show that our novel loss functions are significantly better at dealing with unknown inputs from datasets such as Devanagari, NotMNIST, CIFAR-100 and SVHN.

Clustering is an unsupervised technique for machine learning and data analysis. Different clustering methods such as centroid, connectivity, density, or distribution-based clustering have been applied as a step in many vision applications. Recently, face clustering has become an important task in the face recognition field, and evaluation benchmarks on the LFW and IJB-B datasets have been created. In this paper, we present the Ensembles of Centroids Leveraging Iteratively Processed Spatial Eclipse (ECLIPSE) clustering algorithm, where we combine the advantages of centroid, density, and connectivity-based clustering algorithms. We show that ECLIPSE can work with most kinds of distance measures such as Euclidean, Cosine, and Bray-Curtis distance. We present the Alignment-Free Facial Feature Extraction (AFFFE) network to extract deep features for the LFW and IJB-B datasets. Using these features, our experimental results show that ECLIPSE can estimate the true number of clusters better than related algorithms and delivers state-of-the-art clustering results, especially for large datasets. Using only the hint in the IJB-B protocol, AFFFE and ECLIPSE significantly advance the state of the art.

Machine learning models, including state-of-the-art deep neural networks, are vulnerable to small perturbations that cause unexpected classification errors. This unexpected lack of robustness raises fundamental questions about their generalization properties and poses a serious concern for practical deployments. As such perturbations can remain imperceptible - the formed adversarial examples demonstrate an inherent inconsistency between vulnerable machine learning models and human perception - some prior work casts this problem as a security issue. Despite the significance of the discovered instabilities and ensuing research, their cause is not well understood and no effective method has been developed to address the problem. In this paper, we present a novel theory to explain why this unpleasant phenomenon exists in deep neural networks. Based on that theory, we introduce a simple, efficient, and effective training approach, Batch Adjusted Network Gradients (BANG), which significantly improves the robustness of machine learning models. While the BANG technique does not rely on any form of data augmentation or the utilization of adversarial images for training, the resultant classifiers are more resistant to adversarial perturbations while maintaining or even enhancing the overall classification performance.

Face detection and recognition benchmarks have shifted toward more difficult environments. The challenge presented in this paper addresses the next step in the direction of automatic detection and identification of people from outdoor surveillance cameras. While face detection has shown remarkable success in images collected from the web, surveillance cameras include more diverse occlusions, poses, weather conditions and image blur. Although face verification or closed-set face identification have surpassed human capabilities on some datasets, open-set identification is much more complex as it needs to reject both unknown identities and false accepts from the face detector. We show that unconstrained face detection can approach high detection rates albeit with moderate false accept rates. By contrast, open-set face recognition is currently weak and requires much more attention.

Facial attributes are soft-biometrics that allow limiting the search space, e.g., by rejecting identities with non-matching facial characteristics such as nose sizes or eyebrow shapes. In this paper, we investigate how the latest versions of deep convolutional neural networks, ResNets, perform on the facial attribute classification task. We test two loss functions: the sigmoid cross-entropy loss and the Euclidean loss, and find that for classification performance there is little difference between these two. 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. More significantly, we introduce the Alignment-Free Facial Attribute Classification Technique (AFFACT), a data augmentation technique that allows a network to classify facial attributes without requiring alignment beyond detected face bounding boxes. To our best knowledge, we are the first to report similar accuracy when using only the detected bounding boxes - rather than requiring alignment based on automatically detected facial landmarks - and who can improve classification accuracy with rotating and scaling test images. We show that this approach outperforms the CelebA baseline on unaligned images with a relative improvement of 36.8 %.

Deep neural networks provide state-of-the-art performance on various tasks and are, therefore, widely used in real world applications. DNNs are becoming frequently utilized in biometrics for extracting deep features, which can be used in recognition systems for enrolling and recognizing new individuals. It was revealed that deep neural networks suffer from a fundamental problem, namely, they can unexpectedly misclassify examples formed by slightly perturbing correctly recognized inputs. Various approaches have been developed for generating these so-called adversarial examples, but they aim at attacking end-to-end networks. For biometrics, it is natural to ask whether systems using deep features are immune to or, at least, more resilient to attacks than end-to-end networks. In this paper, we introduce a general technique called the layerwise origin-target synthesis (LOTS) that can be efficiently used to form adversarial examples that mimic the deep features of the target. We analyze and compare the adversarial robustness of the end-to-end VGG Face network with systems that use Euclidean or cosine distance between gallery templates and extracted 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.

Typically, most network intrusion detection systems use supervised learning techniques to identify network anomalies. A problem exists when identifying the unknowns and automatically updating a classifier with new query classes. This is defined as an open set incremental learning problem and we propose to extend a recently introduced method, the Extreme Value Machine (EVM) to address the issue of identifying new classes during query time. The EVM is derived from the statistical extreme value theory and is the first classifier that can perform kernel-free, nonlinear, variable bandwidth outlier detection combined with incremental learning. In this paper, we utilize the EVM for intrusion detection and measure the open set recognition performance of identifying known and unknown classes. Additionally, we evaluate the performance on the KDDCUP'99 dataset and compare the results with the state-of-the-art Weibull-SVM (W-SVM). Our findings demonstrate that the EVM mirrors the performance of the W-SVM classifier, while it supports incremental learning.

Machine learning models are vulnerable to adversarial examples formed by applying small carefully chosen perturbations to inputs that cause unexpected classification errors. 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. We compare the adversarial example generation techniques with respect to the quality of the produced images, and measure the robustness of the tested machine learning models to adversarial examples. Finally, we conduct large-scale experiments on cross-model adversarial portability. We find that adversarial examples are mostly transferable across similar network topologies, and we demonstrate that better machine learning models are less vulnerable to adversarial examples.

Facial attributes are emerging soft biometrics that have the potential to reject non-matches, for example, based on mismatching gender. To be usable in stand-alone systems, facial attributes must be extracted from images automatically and reliably. In this paper, we propose a simple yet effective solution for automatic facial attribute extraction by training a deep convolutional neural network (DCNN) for each facial attribute separately, without using any pre-training or dataset augmentation, and we obtain new state-of-the-art facial attribute classification results on the CelebA benchmark. To test the stability of the networks, we generated adversarial images - formed by adding imperceptible non-random perturbations to original inputs which result in classification errors - via a novel fast flipping attribute (FFA) technique. 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. This result is surprising because no DCNNs tested to date have exhibited robustness to adversarial images without explicit augmentation in the training procedure to account for adversarial examples. Finally, we introduce the concept of natural adversarial samples, i.e., images that are misclassified but can be easily turned into correctly classified images by applying small perturbations. We demonstrate that natural adversarial samples commonly occur, even within the training set, and show that many of these images remain misclassified even with additional training epochs. This phenomenon is surprising because correcting the misclassification, particularly when guided by training data, should require only a small adjustment to the DCNN parameters.

Bob is a free signal processing and machine learning toolbox originally developed by the Biometrics group at Idiap Research Institute, Switzerland. The toolbox is designed to meet the needs of researchers by reducing development time and efficiently processing data. Firstly, Bob provides a researcher-friendly Python environment for rapid development. Secondly, efficient processing of large amounts of multimedia data is provided by fast C++ implementations of identified bottlenecks. The Python environment is integrated seamlessly with the C++ library, which ensures the library is easy to use and extensible. Thirdly, Bob supports reproducible research through its integrated experimental protocols for several databases. Finally, a strong emphasis is placed on code clarity, documentation, and thorough unit testing. Bob is thus an attractive resource for researchers due to this unique combination of ease of use, efficiency, extensibility and transparency. Bob is an open-source library and an ongoing community effort.

We present an integrated face recognition system that combines a Maximum Likelihood (ML) estimator with Gabor graphs for face detection under varying scale and in-plane rotation and matching as well as a Bayesian intrapersonal/extrapersonal classifier (BIC) on graph similarities for face recognition. We have tested a variety of similarity functions and achieved verification rates (at FAR 0.1%) of 90.5% on expression-variation and 95.8% on size-varying frontal images within the CAS-PEAL database. Performing Experiment 1 of FRGC ver2.0, the method achieved a verification rate of 72%.