Aiming to reduce the computational cost of Softmax in massive label space of Face Recognition (FR) benchmarks, recent studies estimate the output using a subset of identities. Although promising, the association between the computation cost and the number of identities in the dataset remains linear only with a reduced ratio. A shared characteristic among available FR methods is the employment of atomic scalar labels during training. Consequently, the input to label matching is through a dot product between the feature vector of the input and the Softmax centroids. Inspired by generative modeling, we present a simple yet effective method that substitutes scalar labels with structured identity code, i.e., a sequence of integers. Specifically, we propose a tokenization scheme that transforms atomic scalar labels into structured identity codes. Then, we train an FR backbone to predict the code for each input instead of its scalar label. As a result, the associated computational cost becomes logarithmic w.r.t. number of identities. We demonstrate the benefits of the proposed method by conducting experiments. In particular, our method outperforms its competitors by 1.52%, and 0.6% at TAR@FAR= le — 4 on IJB- B and IJB-C, respectively, while transforming the association between computational cost and the number of identities from linear to logarithmic. Code

Video anomaly detection aims to develop automated models capable of identifying abnormal events in surveillance videos. The benchmark setup for this task is extremely challenging due to: i) the limited size of the training sets, ii) weak supervision provided in terms of video-level labels, and iii) intrinsic class imbalance induced by the scarcity of abnormal events. In this work, we show that distilling knowledge from aggregated representations of multiple backbones into a single-backbone Student model achieves state-of-the-art performance. In particular, we develop a bi-level distillation approach along with a novel disen-tangled cross-attention-based feature aggregation network. Our proposed approach, DAKD (Distilling Aggregated Knowledge with Disentangled Attention), demonstrates superior performance compared to existing methods across multiple benchmark datasets. Notably, we achieve significant improvements of 1.36%, 0.78%, and 7.02% on the UCF-Crime, ShanghaiTech, and XD-Violence datasets, respectively.

Dataset Condensation (DC) aims to reduce deep neural networks training efforts by synthesizing a small dataset such that it will be as effective as the original large dataset. Conventionally, DC relies on a costly bi-level optimization which prohibits its practicality. Recent research formulates DC as a distribution matching problem which circumvents the costly bi-level optimization. However, this efficiency sacrifices the DC performance. To investigate this performance degradation, we decomposed the dataset distribution into content and style. Our observations indicate two major shortcomings of: 1) style discrepancy between original and condensed data, and 2) limited intra-class diversity of condensed dataset. We present a simple yet effective method to match the style information between original and condensed data, employing statistical moments of feature maps as well-established style indicators. Moreover, we enhance the intra-class diversity by maximizing the Kullback-Leibler divergence within each synthetic class, i.e., content. We demonstrate the efficacy of our method through experiments on diverse datasets of varying size and resolution, achieving improvements of up to 4.1% on CI-FAR 10, 4.2% on CIFAR100, 4.3% on TinyImageNet, 2.0% on ImageNet-1K, 3.3% on ImageWoof, 2.5% on ImageNette, and 5.5% in continual learning accuracy. Code

Laboratory automation integrates robotics, machine learning, and computer vision to enhance precision and efficiency while reducing costs. Despite its pivotal importance in fully automated experimentation, automatic monitoring of procedures is an overlooked task. In this paper, we aim to address this shortcoming by developing a learning method for detecting anomalies in the laboratory setting. To formalize the problem, we focus on the liquid transfer task as a major task in laboratory automation, given the frequent need for reagent mixing and solution preparation. We introduce a novel video anomaly detection framework that leverages the robust CLIP features in conjunction with a transformer encoder. Through an array of experiments and ablation studies, we demonstrate that our proposed method surpasses current state-of-the-art anomaly detection techniques adapted to laboratory automation by a notable margin of over 11%, achieving an impressive AUC of 98.79% for video-level anomaly detection.

Aiming to enhance the utilization of metric space by the parametric softmax classifier, recent studies suggest replacing it with a non-parametric alternative. Although a nonparametric classifier may provide better metric space utilization, it introduces the challenge of capturing inter-class relationships. A shared characteristic among prior nonparametric classifiers is the static assignment of labels to prototypes during the training, i.e., each prototype consistently represents a class throughout the training course. Orthogonal to previous works, we present a simple yet effective method to optimize the category assigned to each prototype (label-to-prototype assignment) during the training. To this aim, we formalize the problem as a two-step optimization objective over network parameters and label-to-prototype assignment mapping. We solve this optimization using a sequential combination of gradient descent and Bi-partide matching. We demonstrate the benefits of the proposed approach by conducting experiments on balanced and long-tail classification problems using different backbone network architectures. In particular, our method outperforms its competitors by 1.22% accuracy on CIFAR-100, and 2.15% on ImageNet-200 using a metric space dimension half of the size of its competitors. Code

Quality assessment of fingerprints captured using digital cameras and smartphones, also called fingerphotos, is a challenging problem in biometric recognition systems. As contactless biometric modalities are gaining more attention, their reliability should also be improved. Many factors, such as illumination, image contrast, camera angle, etc., in fingerphoto acquisition introduce various types of distortion that may render the samples useless. Current quality estimation methods developed for fingerprints collected using contact-based sensors are inadequate for fingerphotos. We propose Utility guided Fingerphoto Quality Assessment (UFQA), a self-supervised dual encoder framework to learn meaningful feature representations to assess fingerphoto quality. A quality prediction model is trained to assess fingerphoto quality with additional supervision of quality maps. The quality metric is a predictor of the utility of fingerphotos in matching scenarios. Therefore, we use a holistic approach by including fingerphoto utility and local quality when labeling the training data. Experimental results verify that our approach performs better than the widely used fingerprint quality metric NFIQ2.2 and state-of-the-art image quality assessment algorithms on multiple publicly available fingerphoto datasets.

Medical image analysis has become increasingly important as it can effectively assist health care providers with precise clinical diagnosis decisions. Thoracic diseases are one of the leading causes of death in the U.S. Accurate and reliable thoracic disease classification plays a crucial role in early diagnosis and consequently proper treatment plans by providing great assistance to physicians. In the health care domain, clinical diagnoses and decisions are made based on specialist’s opinions which is a tedious and error-prone process. Therefore, computer-aided systems are significantly applied to help health care administrations in decision making as a decision support. Deep learning approaches have shown promising potential in clinical image processing. In this study, an online feature selection method for efficient sampling of high-resolution X-ray images is proposed. A weakly-supervised approach that combines DenseNet-121 layers with a saliency sampling approach to extract the most informative parts or pixels of the input images is proposed. Unlike uniform sampling, the proposed approach preserves the spatial information of input images contributing to an accurate prediction. Performance of the proposed model is evaluated using two public chest X-ray datasets including ChestX-ray14 and CheXpert. The final model that aggregates the predictions over multiple sampling of the input image achieves the averaged AUC of 0.890 and 0.921 for ChestX-ray14 and CheXpert datasets, respectively. Our results for thoracic disease detection demonstrate that the proposed approach can effectively improve the performance of the thoracic disease prediction by identifying and preserving the most important parts of the input images.

Optical coherence tomography (OCT) is one of the noninvasive and easy-to-acquire biomarkers (the thickness of the retinal layers, which is detectable within OCT scans) being investigated to diagnose Alzheimer’s disease (AD). This work aims to segment the OCT images automatically; however, it is a challenging task due to various issues such as the speckle noise, small target region, and unfavorable imaging conditions. In our previous work, we have proposed the multi-stage & multi-discriminatory generative adversarial network (MultiSDGAN) [1] to translate OCT scans in high-resolution segmentation labels. In this investigation, we aim to evaluate and compare various combinations of channel and spatial attention to the MultiSDGAN architecture to extract more powerful feature maps by capturing rich contextual relationships to improve segmentation performance. Moreover, we developed and evaluated a guided mutli-stage attention framework where we incorporated a guided attention mechanism by forcing an L-1 loss between a specifically designed binary mask and the generated attention maps. Our ablation study results on the WVU-OCT data-set in five-fold cross-validation (5-CV) suggest that the proposed MultiSDGAN with a serial attention module provides the most competitive performance, and guiding the spatial attention feature maps by binary masks further improves the performance in our proposed network. Comparing the baseline model with adding the guided-attention, our results demonstrated relative improvements of 21.44% and 19.45% on the Dice coefficient and SSIM, respectively.

This paper presents a supervised mixing augmentation method termed SuperMix, which exploits the salient regions within input images to construct mixed training samples. SuperMix is designed to obtain mixed images rich in visual features and complying with realistic image priors. To enhance the efficiency of the algorithm, we develop a variant of the Newton iterative method, 65× faster than gradient descent on this problem. We validate the effectiveness of SuperMix through extensive evaluations and ablation studies on two tasks of object classification and knowledge distillation. On the classification task, SuperMix provides comparable performance to the advanced augmentation methods, such as AutoAugment and RandAugment. In particular, combining SuperMix with RandAugment achieves 78.2% top-1 accuracy on ImageNet with ResNet50. On the distillation task, solely classifying images mixed using the teacher’s knowledge achieves comparable performance to the state-of-the-art distillation methods. Furthermore, on average, incorporating mixed images into the distillation objective improves the performance by 3.4% and 3.1% on CIFAR-100 and ImageNet, respectively. The code is available at https://github.com/alldbi/SuperMix.

The goal is to use Wasserstein metric to provide pseudo labels for the unlabeled images to train a Convolutional Neural Networks (CNN) in a Semi-Supervised Learning (SSL) manner for the classification task. The basic premise in our method is that the discrepancy between two discrete empirical measures (e.g., clusters) which come from the same or similar distribution is expected to be less than the case where these measures come from completely two different distributions. In our proposed method, we first pre-train our CNN using a self-supervised learning method to make a cluster assumption on the unlabeled images. Next, inspired by the Wasserstein metric which considers the geometry of the metric space to provide a natural notion of similarity between discrete empirical measures, we leverage it to cluster the unlabeled images and then match the clusters to their similar class of labeled images to provide a pseudo label for the data within each cluster. We have evaluated and compared our method with state-of-the-art SSL methods on the standard datasets to demonstrate its effectiveness.

While working with fingerprint images acquired from crime scenes, mobile cameras, or low-quality sensors, it becomes difficult for automated identification systems to verify the identity due to image blur and distortion. We propose a fingerprint deblurring model FDeblur-GAN, based on the conditional Generative Adversarial Networks (cGANs) and multi-stage framework of the stack GAN. Additionally, we integrate two auxiliary sub-networks into the model for the deblurring task. The first sub-network is a ridge extractor model. It is added to generate ridge maps to ensure that fingerprint information and minutiae are preserved in the deblurring process and prevent the model from generating erroneous minutiae. The second sub-network is a verifier that helps the generator to preserve the ID information during the generation process. Using a database of blurred fingerprints and corresponding ridge maps, the deep network learns to deblur from the input blurry samples. We evaluate the proposed method in combination with two different fingerprint matching algorithms. We achieved an accuracy of 95.18% on our fingerprint database for the task of matching deblurred and ground truth fingerprints.

In this paper, we present a novel differential morph detection framework, utilizing landmark and appearance disentanglement. In our framework, the face image is represented in the embedding domain using two disentangled but complementary representations. The network is trained by triplets of face images, in which the intermediate image inherits the landmarks from one image and the appearance from the other image. This initially trained network is further trained for each dataset using contrastive representations. We demonstrate that, by employing appearance and landmark disentanglement, the proposed frame-work can provide state-of-the-art differential morph detection performance. This functionality is achieved by the using distances in landmark, appearance, and ID domains. The performance of the proposed framework is evaluated using three morph datasets generated with different methodologies.

Recently, ensemble models have demonstrated empirical capabilities to alleviate the adversarial vulnerability. In this paper, we exploit first-order interactions within ensembles to formalize a reliable and practical defense. We introduce a scenario of interactions that certifiably improves the robustness according to the size of the ensemble, the diversity of the gradient directions, and the balance of the member's contribution to the robustness. We present a joint gradient phase and magnitude regularization (GPMR) as a vigorous approach to impose the desired scenario of interactions among members of the ensemble. Through extensive experiments, including gradient-based and gradient-free evaluations on several datasets and network architectures, we validate the practical effectiveness of the proposed approach compared to the previous methods. Furthermore, we demonstrate that GPMR is orthogonal to other defense strategies developed for single classifiers and their combination can further improve the robustness of ensembles.

In this work, we propose a Neural Architecture Search (NAS) for retinal layer segmentation in Optical Coherence Tomography (OCT) scans. We incorporate the Unet architecture in the NAS framework as its backbone for the segmentation of the retinal layers in our collected and preprocessed OCT image dataset. At the pre-processing stage, we conduct super resolution and image processing techniques on the raw OCT scans to improve the quality of the raw images. For our search strategy, different primitive operations are suggested to find the down- & up-sampling cell blocks, and the binary gate method is applied to make the search strategy practical for the task in hand. We empirically evaluated our method on our in-house OCT dataset. The experimental results demonstrate that the self-adapting NAS-Unet architecture substantially outperformed the competitive human-designed architecture by achieving 95.4% in mean Intersection over Union metric and 78.7% in Dice similarity coefficient.

Performance of fingerprint recognition algorithms substantially rely on fine features extracted from fingerprints. Apart from minutiae and ridge patterns, pore features have proven to be usable for fingerprint recognition. Although features from minutiae and ridge patterns are quite attainable from low-resolution images, using pore features is practical only if the fingerprint image is of high resolution which necessitates a model that enhances the image quality of the conventional 500 ppi legacy fingerprints preserving the fine details. To find a solution for recovering pore information from low-resolution fingerprints, we adopt a joint learning-based approach that combines both super-resolution and pore detection networks. Our modified single image Super-Resolution Generative Adversarial Network (SRGAN) framework helps to reliably reconstruct high-resolution fingerprint samples from low-resolution ones assisting the pore detection network to identify pores with a high accuracy. The network jointly learns a distinctive feature representation from a real low-resolution fingerprint sample and successfully synthesizes a high-resolution sample from it. To add discriminative information and uniqueness for all the subjects, we have integrated features extracted from a deep fingerprint verifier with the SRGAN quality discriminator. We also add ridge reconstruction loss, utilizing ridge patterns to make the best use of extracted features. Our proposed method solves the recognition problem by improving the quality of fingerprint images. High recognition accuracy of the synthesized samples that is close to the accuracy achieved using the original high-resolution images validate the effectiveness of our proposed model.

Deep neural networks are susceptible to adversarial manipulations in the input domain. The extent of vulnerability has been explored intensively in cases of ℓp-bounded and ℓp-minimal adversarial perturbations. However, the vulnerability of DNNs to adversarial perturbations with specific statistical properties or frequency-domain characteristics has not been sufficiently explored. In this paper, we study the smoothness of perturbations and propose Smooth-Fool, a general and computationally efficient framework for computing smooth adversarial perturbations. Through extensive experiments, we validate the efficacy of the proposed method for both the white-box and black-box attack scenarios. In particular, we demonstrate that: (i) there exist extremely smooth adversarial perturbations for well-established and widely used network architectures, (ii) smoothness significantly enhances the robustness of perturbations against state-of-the-art defense mechanisms, (iii) smoothness improves the transferability of adversarial perturbations across both data points and network architectures, and (iv) class categories exhibit a variable range of susceptibility to smooth perturbations. Our results suggest that smooth APs can play a significant role in exploring the vulnerability extent of DNNs to adversarial examples. The code is available at https://github.com/alldbi/SmoothFool.

In this paper, we propose a framework for disentangling the appearance and geometry representations in the face recognition task. To provide supervision for this aim, we generate geometrically identical faces by incorporating spatial transformations. We demonstrate that the proposed approach enhances the performance of deep face recognition models by assisting the training process in two ways. First, it enforces the early and intermediate convolutional layers to learn more representative features that satisfy the properties of disentangled embeddings. Second, it augments the training set by altering faces geometrically. Through extensive experiments, we demonstrate that integrating the proposed approach into state-of-the-art face recognition methods effectively improves their performance on challenging datasets, such as LFW, YTF, and MegaFace. Both theoretical and practical aspects of the method are analyzed rigorously by concerning ablation studies and knowledge transfer tasks. Furthermore, we show that the knowledge leaned by the proposed method can favor other face-related tasks, such as attribute prediction.

In this work, we present a practical approach to the problem of facial landmark detection. The proposed method can deal with large shape and appearance variations under the rich shape deformation. To handle the shape variations we equip our method with the aggregation of manipulated face images. The proposed framework generates different manipulated faces using only one given face image. The approach utilizes the fact that small but carefully crafted geometric manipulation in the input domain can fool deep face recognition models. We propose three different approaches to generate manipulated faces in which two of them perform the manipulations via adversarial attacks and the other one uses known transformations. Aggregating the manipulated faces provides a more robust landmark detection approach which is able to capture more important deformations and variations of the face shapes. Our approach is demonstrated its superiority compared to the state-of-the-art method on benchmark datasets AFLW, 300-W, and COFW.

Objects are usually organized in a hierarchical structure in which each coarse category (e.g., big cat) corresponds to a superclass of several fine categories (e.g., cheetah, leopard). The objects grouped within the same coarse category, but in different fine categories, usually share a set of global visual features; however, these objects have distinctive local properties that characterize them at a fine level. This paper addresses the challenge of fine image classification in a weakly supervised fashion, whereby a subset of images is tagged by fine labels, while the remaining are tagged by coarse labels. We propose a new deep model that leverages coarse images to improve the classification performance of fine images within the coarse category. Our model is an end to end framework consisting of a Convolutional Neural Network (CNN) which uses both fine and coarse images to tune its parameters. The CNN outputs are then fanned out into two separate branches such that the first branch uses a supervised low rank self expressive layer to project the CNN outputs to the low rank subspaces to capture the global structures for the coarse classification, while the other branch uses a supervised sparse self expressive layer to project them to the sparse subspaces to capture the local structures for the fine classification. Our deep model uses coarse images in conjunction with fine images to jointly explore the low rank and sparse subspaces by sharing the parameters during the training which causes the data points obtained by the CNN to be well-projected to both sparse and low rank subspaces for classification.

The state-of-the-art performance of deep learning algorithms has led to a considerable increase in the utilization of machine learning in security-sensitive and critical applications. However, it has recently been shown that a small and carefully crafted perturbation in the input space can completely fool a deep model. In this study, we explore the extent to which face recognition systems are vulnerable to geometrically-perturbed adversarial faces. We propose a fast landmark manipulation method for generating adversarial faces, which is approximately 200 times faster than the previous geometric attacks and obtains 99.86% success rate on the state-of-the-art face recognition models. To further force the generated samples to be natural, we introduce a second attack constrained on the semantic structure of the face which has the half speed of the first attack with the success rate of 99.96%. Both attacks are extremely robust against the state-of-the-art defense methods with the success rate of equal or greater than 53.59%. Code is available at https://github.com/alldbi/FLM.

In this paper, we propose a deep multimodal fusion network to fuse multiple modalities (face, iris, and fingerprint) for person identification. The proposed deep multimodal fusion algorithm consists of multiple streams of modality-specific Convolutional Neural Networks (CNNs), which are jointly optimized at multiple feature abstraction levels. Multiple features are extracted at several different convolutional layers from each modality-specific CNN for joint feature fusion, optimization, and classification. Features extracted at different convolutional layers of a modality-specific CNN represent the input at several different levels of abstract representations. We demonstrate that an efficient multimodal classification can be accomplished with a significant reduction in the number of network parameters by exploiting these multi-level abstract representations extracted from all the modality-specific CNNs. We demonstrate an increase in multimodal person identification performance by utilizing the proposed multi-level feature abstract representations in our multimodal fusion, rather than using only the features from the last layer of each modality-specific CNNs. We show that our deep multi-modal CNNs with multimodal fusion at several different feature level abstraction can significantly outperform the unimodal representation accuracy. We also demonstrate that the joint optimization of all the modality-specific CNNs excels the score and decision level fusions of independently optimized CNNs.