Recognizing Families In the Wild (RFIW), held as a data challenge in conjunction with the 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG), is a large-scale, multi-track visual kinship recognition evaluation. This is our fifth edition of RFIW, for which we continue the effort to attract scholars, bring together professionals, publish new work, and discuss prospects. In this paper, we summarize submissions for the three tasks of this year's RFIW: specifically, we review the results for kinship verification, tri-subject verification, and family member search and retrieval. We take a look at the RFIW problem, as well as share current efforts and make recommendations for promising future directions.
In this paper, we introduce a new architecture for few shot learning, the task of teaching a neural network from as few as one or five labeled examples. Inspired by the theoretical results of Alaine et al that Denoising Autoencoders refine features to lie closer to the true data manifold, we present a new training scheme that adds noise at multiple stages of an existing neural architecture while simultaneously learning to be robust to this added noise. This architecture, which we call a Self-Denoising Neural Network (SDNN), can be applied easily to most modern convolutional neural architectures, and can be used as a supplement to many existing few-shot learning techniques. We empirically show that SDNNs out-perform previous state-of-the-art methods for few shot image recognition using the Wide-ResNet architecture on the \textit{mini}ImageNet, tiered-ImageNet, and CIFAR-FS few shot learning datasets. We also perform a series of ablation experiments to empirically justify the construction of the SDNN architecture. Finally, we show that SDNNs even improve few shot performance on the task of human action detection in video using experiments on the ActEV SDL Surprise Activities challenge.
The adversarial attack literature contains a myriad of algorithms for crafting perturbations which yield pathological behavior in neural networks. In many cases, multiple algorithms target the same tasks and even enforce the same constraints. In this work, we show that different attack algorithms produce adversarial examples which are distinct not only in their effectiveness but also in how they qualitatively affect their victims. We begin by demonstrating that one can determine the attack algorithm that crafted an adversarial example. Then, we leverage recent advances in parameter-space saliency maps to show, both visually and quantitatively, that adversarial attack algorithms differ in which parts of the network and image they target. Our findings suggest that prospective adversarial attacks should be compared not only via their success rates at fooling models but also via deeper downstream effects they have on victims.
Face super-resolution is a challenging and highly ill-posed problem since a low-resolution (LR) face image may correspond to multiple high-resolution (HR) ones during the hallucination process and cause a dramatic identity change for the final super-resolved results. Thus, to address this problem, we propose an end-to-end progressive learning framework incorporating facial attributes and enforcing additional supervision from multi-scale discriminators. By incorporating facial attributes into the learning process and progressively resolving the facial image, the mapping between LR and HR images is constrained more, and this significantly helps to reduce the ambiguity and uncertainty in one-to-many mapping. In addition, we conduct thorough evaluations on the CelebA dataset following the settings of previous works (i.e. super-resolving by a factor of 8x from tiny 16x16 face images.), and the results demonstrate that the proposed approach can yield satisfactory face hallucination images outperforming other state-of-the-art approaches.
Manipulated videos, especially those where the identity of an individual has been modified using deep neural networks, are becoming an increasingly relevant threat in the modern day. In this paper, we seek to develop a generalizable, explainable solution to detecting these manipulated videos. To achieve this, we design a series of forgery detection systems that each focus on one individual part of the face. These parts-based detection systems, which can be combined and used together in a single architecture, meet all of our desired criteria - they generalize effectively between datasets and give us valuable insights into what the network is looking at when making its decision. We thus use these detectors to perform detailed empirical analysis on the FaceForensics++, Celeb-DF, and Facebook Deepfake Detection Challenge datasets, examining not just what the detectors find but also collecting and analyzing useful related statistics on the datasets themselves.
In recent years, visible-spectrum face verification systems have been shown to match expert forensic examiner recognition performance. However, such systems are ineffective in low-light and nighttime conditions. Thermal face imagery, which captures body heat emissions, effectively augments the visible spectrum, capturing discriminative facial features in scenes with limited illumination. Due to the increased cost and difficulty of obtaining diverse, paired thermal and visible spectrum datasets, algorithms and large-scale benchmarks for low-light recognition are limited. This paper presents an algorithm that achieves state-of-the-art performance on both the ARL-VTF and TUFTS multi-spectral face datasets. Importantly, we study the impact of face alignment, pixel-level correspondence, and identity classification with label smoothing for multi-spectral face synthesis and verification. We show that our proposed method is widely applicable, robust, and highly effective. In addition, we show that the proposed method significantly outperforms face frontalization methods on profile-to-frontal verification. Finally, we present MILAB-VTF(B), a challenging multi-spectral face dataset that is composed of paired thermal and visible videos. To the best of our knowledge, with face data from 400 subjects, this dataset represents the most extensive collection of publicly available indoor and long-range outdoor thermal-visible face imagery. Lastly, we show that our end-to-end thermal-to-visible face verification system provides strong performance on the MILAB-VTF(B) dataset.
Face recognition networks encode information about sensitive attributes while being trained for identity classification. Such encoding has two major issues: (a) it makes the face representations susceptible to privacy leakage (b) it appears to contribute to bias in face recognition. However, existing bias mitigation approaches generally require end-to-end training and are unable to achieve high verification accuracy. Therefore, we present a descriptor-based adversarial de-biasing approach called `Protected Attribute Suppression System (PASS)'. PASS can be trained on top of descriptors obtained from any previously trained high-performing network to classify identities and simultaneously reduce encoding of sensitive attributes. This eliminates the need for end-to-end training. As a component of PASS, we present a novel discriminator training strategy that discourages a network from encoding protected attribute information. We show the efficacy of PASS to reduce gender and skintone information in descriptors from SOTA face recognition networks like Arcface. As a result, PASS descriptors outperform existing baselines in reducing gender and skintone bias on the IJB-C dataset, while maintaining a high verification accuracy.
Boosting is a method for finding a highly accurate hypothesis by linearly combining many ``weak" hypotheses, each of which may be only moderately accurate. Thus, boosting is a method for learning an ensemble of classifiers. While boosting has been shown to be very effective for decision trees, its impact on neural networks has not been extensively studied. We prove one important difference between sums of decision trees compared to sums of convolutional neural networks (CNNs) which is that a sum of decision trees cannot be represented by a single decision tree with the same number of parameters while a sum of CNNs can be represented by a single CNN. Next, using standard object recognition datasets, we verify experimentally the well-known result that a boosted ensemble of decision trees usually generalizes much better on testing data than a single decision tree with the same number of parameters. In contrast, using the same datasets and boosting algorithms, our experiments show the opposite to be true when using neural networks (both CNNs and multilayer perceptrons (MLPs)). We find that a single neural network usually generalizes better than a boosted ensemble of smaller neural networks with the same total number of parameters.
As the curation of data for machine learning becomes increasingly automated, dataset tampering is a mounting threat. Backdoor attackers tamper with training data to embed a vulnerability in models that are trained on that data. This vulnerability is then activated at inference time by placing a "trigger" into the model's input. Typical backdoor attacks insert the trigger directly into the training data, although the presence of such an attack may be visible upon inspection. In contrast, the Hidden Trigger Backdoor Attack achieves poisoning without placing a trigger into the training data at all. However, this hidden trigger attack is ineffective at poisoning neural networks trained from scratch. We develop a new hidden trigger attack, Sleeper Agent, which employs gradient matching, data selection, and target model re-training during the crafting process. Sleeper Agent is the first hidden trigger backdoor attack to be effective against neural networks trained from scratch. We demonstrate its effectiveness on ImageNet and in black-box settings. Our implementation code can be found at https://github.com/hsouri/Sleeper-Agent.
Urban material recognition in remote sensing imagery is a highly relevant, yet extremely challenging problem due to the difficulty of obtaining human annotations, especially on low resolution satellite images. To this end, we propose an unsupervised domain adaptation based approach using adversarial learning. We aim to harvest information from smaller quantities of high resolution data (source domain) and utilize the same to super-resolve low resolution imagery (target domain). This can potentially aid in semantic as well as material label transfer from a richly annotated source to a target domain.