Text-Guided Face Recognition using Multi-Granularity Cross-Modal Contrastive Learning

State-of-the-art face recognition (FR) models often experience a significant performance drop when dealing with facial images in surveillance scenarios where images are in low quality and often corrupted with noise. Leveraging facial characteristics, such as freckles, scars, gender, and ethnicity, becomes highly beneficial in improving FR performance in such scenarios. In this paper, we introduce text-guided face recognition (TGFR) to analyze the impact of integrating facial attributes in the form of natural language descriptions. We hypothesize that adding semantic information into the loop can significantly improve the image understanding capability of an FR algorithm compared to other soft biometrics. However, learning a discriminative joint embedding within the multimodal space poses a considerable challenge due to the semantic gap in the unaligned image-text representations, along with the complexities arising from ambiguous and incoherent textual descriptions of the face. To address these challenges, we introduce a face-caption alignment module (FCAM), which incorporates cross-modal contrastive losses across multiple granularities to maximize the mutual information between local and global features of the face-caption pair. Within FCAM, we refine both facial and textual features for learning aligned and discriminative features. We also design a face-caption fusion module (FCFM) that applies fine-grained interactions and coarse-grained associations among cross-modal features. Through extensive experiments conducted on three face-caption datasets, proposed TGFR demonstrates remarkable improvements, particularly on low-quality images, over existing FR models and outperforms other related methods and benchmarks.

A Universal Anti-Spoofing Approach for Contactless Fingerprint Biometric Systems

With the increasing integration of smartphones into our daily lives, fingerphotos are becoming a potential contactless authentication method. While it offers convenience, it is also more vulnerable to spoofing using various presentation attack instruments (PAI). The contactless fingerprint is an emerging biometric authentication but has not yet been heavily investigated for anti-spoofing. While existing anti-spoofing approaches demonstrated fair results, they have encountered challenges in terms of universality and scalability to detect any unseen/unknown spoofed samples. To address this issue, we propose a universal presentation attack detection method for contactless fingerprints, despite having limited knowledge of presentation attack samples. We generated synthetic contactless fingerprints using StyleGAN from live finger photos and integrating them to train a semi-supervised ResNet-18 model. A novel joint loss function, combining the Arcface and Center loss, is introduced with a regularization to balance between the two loss functions and minimize the variations within the live samples while enhancing the inter-class variations between the deepfake and live samples. We also conducted a comprehensive comparison of different regularizations' impact on the joint loss function for presentation attack detection (PAD) and explored the performance of a modified ResNet-18 architecture with different activation functions (i.e., leaky ReLU and RelU) in conjunction with Arcface and center loss. Finally, we evaluate the performance of the model using unseen types of spoof attacks and live data. Our proposed method achieves a Bona Fide Classification Error Rate (BPCER) of 0.12\%, an Attack Presentation Classification Error Rate (APCER) of 0.63\%, and an Average Classification Error Rate (ACER) of 0.37\%.

Synthetic Latent Fingerprint Generation Using Style Transfer

Limited data availability is a challenging problem in the latent fingerprint domain. Synthetically generated fingerprints are vital for training data-hungry neural network-based algorithms. Conventional methods distort clean fingerprints to generate synthetic latent fingerprints. We propose a simple and effective approach using style transfer and image blending to synthesize realistic latent fingerprints. Our evaluation criteria and experiments demonstrate that the generated synthetic latent fingerprints preserve the identity information from the input contact-based fingerprints while possessing similar characteristics as real latent fingerprints. Additionally, we show that the generated fingerprints exhibit several qualities and styles, suggesting that the proposed method can generate multiple samples from a single fingerprint.

Improving Face Recognition from Caption Supervision with Multi-Granular Contextual Feature Aggregation

We introduce caption-guided face recognition (CGFR) as a new framework to improve the performance of commercial-off-the-shelf (COTS) face recognition (FR) systems. In contrast to combining soft biometrics (eg., facial marks, gender, and age) with face images, in this work, we use facial descriptions provided by face examiners as a piece of auxiliary information. However, due to the heterogeneity of the modalities, improving the performance by directly fusing the textual and facial features is very challenging, as both lie in different embedding spaces. In this paper, we propose a contextual feature aggregation module (CFAM) that addresses this issue by effectively exploiting the fine-grained word-region interaction and global image-caption association. Specifically, CFAM adopts a self-attention and a cross-attention scheme for improving the intra-modality and inter-modality relationship between the image and textual features, respectively. Additionally, we design a textual feature refinement module (TFRM) that refines the textual features of the pre-trained BERT encoder by updating the contextual embeddings. This module enhances the discriminative power of textual features with a cross-modal projection loss and realigns the word and caption embeddings with visual features by incorporating a visual-semantic alignment loss. We implemented the proposed CGFR framework on two face recognition models (ArcFace and AdaFace) and evaluated its performance on the Multi-Modal CelebA-HQ dataset. Our framework significantly improves the performance of ArcFace in both 1:1 verification and 1:N identification protocol.

Benchmarking Human Face Similarity Using Identical Twins

The problem of distinguishing identical twins and non-twin look-alikes in automated facial recognition (FR) applications has become increasingly important with the widespread adoption of facial biometrics. Due to the high facial similarity of both identical twins and look-alikes, these face pairs represent the hardest cases presented to facial recognition tools. This work presents an application of one of the largest twin datasets compiled to date to address two FR challenges: 1) determining a baseline measure of facial similarity between identical twins and 2) applying this similarity measure to determine the impact of doppelgangers, or look-alikes, on FR performance for large face datasets. The facial similarity measure is determined via a deep convolutional neural network. This network is trained on a tailored verification task designed to encourage the network to group together highly similar face pairs in the embedding space and achieves a test AUC of 0.9799. The proposed network provides a quantitative similarity score for any two given faces and has been applied to large-scale face datasets to identify similar face pairs. An additional analysis which correlates the comparison score returned by a facial recognition tool and the similarity score returned by the proposed network has also been performed.

Synthesis-Guided Feature Learning for Cross-Spectral Periocular Recognition

A common yet challenging scenario in periocular biometrics is cross-spectral matching - in particular, the matching of visible wavelength against near-infrared (NIR) periocular images. We propose a novel approach to cross-spectral periocular verification that primarily focuses on learning a mapping from visible and NIR periocular images to a shared latent representational subspace, and supports this effort by simultaneously learning intra-spectral image reconstruction. We show the auxiliary image reconstruction task (and in particular the reconstruction of high-level, semantic features) results in learning a more discriminative, domain-invariant subspace compared to the baseline while incurring no additional computational or memory costs at test-time. The proposed Coupled Conditional Generative Adversarial Network (CoGAN) architecture uses paired generator networks (one operating on visible images and the other on NIR) composed of U-Nets with ResNet-18 encoders trained for feature learning via contrastive loss and for intra-spectral image reconstruction with adversarial, pixel-based, and perceptual reconstruction losses. Moreover, the proposed CoGAN model beats the current state-of-art (SotA) in cross-spectral periocular recognition. On the Hong Kong PolyU benchmark dataset, we achieve 98.65% AUC and 5.14% EER compared to the SotA EER of 8.02%. On the Cross-Eyed dataset, we achieve 99.31% AUC and 3.99% EER versus SotA EER of 4.39%.

Deep Hashing for Secure Multimodal Biometrics

When compared to unimodal systems, multimodal biometric systems have several advantages, including lower error rate, higher accuracy, and larger population coverage. However, multimodal systems have an increased demand for integrity and privacy because they must store multiple biometric traits associated with each user. In this paper, we present a deep learning framework for feature-level fusion that generates a secure multimodal template from each user's face and iris biometrics. We integrate a deep hashing (binarization) technique into the fusion architecture to generate a robust binary multimodal shared latent representation. Further, we employ a hybrid secure architecture by combining cancelable biometrics with secure sketch techniques and integrate it with a deep hashing framework, which makes it computationally prohibitive to forge a combination of multiple biometrics that pass the authentication. The efficacy of the proposed approach is shown using a multimodal database of face and iris and it is observed that the matching performance is improved due to the fusion of multiple biometrics. Furthermore, the proposed approach also provides cancelability and unlinkability of the templates along with improved privacy of the biometric data. Additionally, we also test the proposed hashing function for an image retrieval application using a benchmark dataset. The main goal of this paper is to develop a method for integrating multimodal fusion, deep hashing, and biometric security, with an emphasis on structural data from modalities like face and iris. The proposed approach is in no way a general biometric security framework that can be applied to all biometric modalities, as further research is needed to extend the proposed framework to other unconstrained biometric modalities.

Quality Guided Sketch-to-Photo Image Synthesis

Facial sketches drawn by artists are widely used for visual identification applications and mostly by law enforcement agencies, but the quality of these sketches depend on the ability of the artist to clearly replicate all the key facial features that could aid in capturing the true identity of a subject. Recent works have attempted to synthesize these sketches into plausible visual images to improve visual recognition and identification. However, synthesizing photo-realistic images from sketches proves to be an even more challenging task, especially for sensitive applications such as suspect identification. In this work, we propose a novel approach that adopts a generative adversarial network that synthesizes a single sketch into multiple synthetic images with unique attributes like hair color, sex, etc. We incorporate a hybrid discriminator which performs attribute classification of multiple target attributes, a quality guided encoder that minimizes the perceptual dissimilarity of the latent space embedding of the synthesized and real image at different layers in the network and an identity preserving network that maintains the identity of the synthesised image throughout the training process. Our approach is aimed at improving the visual appeal of the synthesised images while incorporating multiple attribute assignment to the generator without compromising the identity of the synthesised image. We synthesised sketches using XDOG filter for the CelebA, WVU Multi-modal and CelebA-HQ datasets and from an auxiliary generator trained on sketches from CUHK, IIT-D and FERET datasets. Our results are impressive compared to current state of the art.

A data-driven proxy to Stoke's flow in porous media

The objective for this work is to develop a data-driven proxy to high-fidelity numerical flow simulations using digital images. The proposed model can capture the flow field and permeability in a large verity of digital porous media based on solid grain geometry and pore size distribution by detailed analyses of the local pore geometry and the local flow fields. To develop the model, the detailed pore space geometry and simulation runs data from 3500 two-dimensional high-fidelity Lattice Boltzmann simulation runs are used to train and to predict the solutions with a high accuracy in much less computational time. The proposed methodology harness the enormous amount of generated data from high-fidelity flow simulations to decode the often under-utilized patterns in simulations and to accurately predict solutions to new cases. The developed model can truly capture the physics of the problem and enhance prediction capabilities of the simulations at a much lower cost. These predictive models, in essence, do not spatio-temporally reduce the order of the problem. They, however, possess the same numerical resolutions as their Lattice Boltzmann simulations equivalents do with the great advantage that their solutions can be achieved by significant reduction in computational costs (speed and memory).

Learning a Mixture of Deep Networks for Single Image Super-Resolution

Single image super-resolution (SR) is an ill-posed problem which aims to recover high-resolution (HR) images from their low-resolution (LR) observations. The crux of this problem lies in learning the complex mapping between low-resolution patches and the corresponding high-resolution patches. Prior arts have used either a mixture of simple regression models or a single non-linear neural network for this propose. This paper proposes the method of learning a mixture of SR inference modules in a unified framework to tackle this problem. Specifically, a number of SR inference modules specialized in different image local patterns are first independently applied on the LR image to obtain various HR estimates, and the resultant HR estimates are adaptively aggregated to form the final HR image. By selecting neural networks as the SR inference module, the whole procedure can be incorporated into a unified network and be optimized jointly. Extensive experiments are conducted to investigate the relation between restoration performance and different network architectures. Compared with other current image SR approaches, our proposed method achieves state-of-the-arts restoration results on a wide range of images consistently while allowing more flexible design choices. The source codes are available in http://www.ifp.illinois.edu/~dingliu2/accv2016.