Search

Nodal lines are one-dimensional topological features of semi-metal band structures along which two bands are degenerate as a result of non-accidental symmetry-protected crossings, and behave topologically as $k$-space vortices in the Berry connection. Here, we present a new class of tilted nodal lines, protected by mirror symmetry, formed from the intersection of three band crossings at a set of critical points. One crossing is gapped out, fusing the remaining two crossings at the shifted critical points to form composite nodal lines. We demonstrate these composite nodal lines are capable of supporting fundamentally different Berry curvature textures than the typical two-band case, despite having a simple ring topology. In addition, we present a realistic model based on cubic, forced-ferromagnetic, EuTiO$_3$, where the spin and orbital degrees of freedom are plentiful enough to allow the material realization of such composite nodal lines. In this system, the composite nature of the nodal line results in a spin Hall conductivity with a non-monotonic dependence on carrier concentration., Comment: 10 pages, 6 Figures

Chiral magnetic textures give rise to unconventional magnetotransport phenomena such as the topological Hall effect and nonreciprocal electronic transport. While the correspondence between real-space magnetic topology/symmetry and such transport phenomena has been well established, a microscopic understanding based on the spin-dependent band structure in momentum space remains elusive. Here we demonstrate how a chiral magnetic structure in real space introduces an asymmetry in the electronic band structure and triggers a nonreciprocal electronic transport in a centrosymmetric helimagnet {\alpha}-EuP$_3$. The magnetic structure of {\alpha}-EuP$_3$ is highly tunable by a magnetic field and closely coupled to its semi-metallic electronic band structure, enabling a systematic study across chiral and achiral magnetic phases on the correspondence between nonreciprocal transport and electronic band asymmetry. Our findings reveal how a microscopic change in the magnetic configuration of charge carriers can lead to nonreciprocal electronic transport, paving the way for designing chiral magnets with desirable properties., Comment: 31 pages, 12 figures, 1 table

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 non-parametric classifier may provide better metric space utilization, it introduces the challenge of capturing inter-class relationships. A shared characteristic among prior non-parametric classifiers is the static assignment of labels to prototypes during the training, ie, 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 Bipartide 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: https://github.com/msed-Ebrahimi/DL2PA_CVPR24, Comment: Accepted to CVPR 2024

Though recent studies have made significant progress in morph attack detection by virtue of deep neural networks, they often fail to generalize well to unseen morph attacks. With numerous morph attacks emerging frequently, generalizable morph attack detection has gained significant attention. This paper focuses on enhancing the generalization capability of morph attack detection from the perspective of consistency regularization. Consistency regularization operates under the premise that generalizable morph attack detection should output consistent predictions irrespective of the possible variations that may occur in the input space. In this work, to reach this objective, two simple yet effective morph-wise augmentations are proposed to explore a wide space of realistic morph transformations in our consistency regularization. Then, the model is regularized to learn consistently at the logit as well as embedding levels across a wide range of morph-wise augmented images. The proposed consistency regularization aligns the abstraction in the hidden layers of our model across the morph attack images which are generated from diverse domains in the wild. Experimental results demonstrate the superior generalization and robustness performance of our proposed method compared to the state-of-the-art studies., Comment: Accepted to the IEEE International Joint Conference on Biometrics (IJCB), 2023

Deep convolutional neural networks have achieved remarkable success in face recognition (FR), partly due to the abundant data availability. However, the current training benchmarks exhibit an imbalanced quality distribution; most images are of high quality. This poses issues for generalization on hard samples since they are underrepresented during training. In this work, we employ the multi-model boosting technique to deal with this issue. Inspired by the well-known AdaBoost, we propose a sample-level weighting approach to incorporate the importance of different samples into the FR loss. Individual models of the proposed framework are experts at distinct levels of sample hardness. Therefore, the combination of models leads to a robust feature extractor without losing the discriminability on the easy samples. Also, for incorporating the sample hardness into the training criterion, we analytically show the effect of sample mining on the important aspects of current angular margin loss functions, i.e., margin and scale. The proposed method shows superior performance in comparison with the state-of-the-art algorithms in extensive experiments on the CFP-FP, LFW, CPLFW, CALFW, AgeDB, TinyFace, IJB-B, and IJB-C evaluation datasets., Comment: 2023 IEEE International Joint Conference on Biometrics (IJCB)

In recent years, deep face recognition methods have demonstrated impressive results on in-the-wild datasets. However, these methods have shown a significant decline in performance when applied to real-world low-resolution benchmarks like TinyFace or SCFace. To address this challenge, we propose a novel classification consistency knowledge distillation approach that transfers the learned classifier from a high-resolution model to a low-resolution network. This approach helps in finding discriminative representations for low-resolution instances. To further improve the performance, we designed a knowledge distillation loss using the adaptive angular penalty inspired by the success of the popular angular margin loss function. The adaptive penalty reduces overfitting on low-resolution samples and alleviates the convergence issue of the model integrated with data augmentation. Additionally, we utilize an asymmetric cross-resolution learning approach based on the state-of-the-art semi-supervised representation learning paradigm to improve discriminability on low-resolution instances and prevent them from forming a cluster. Our proposed method outperforms state-of-the-art approaches on low-resolution benchmarks, with a three percent improvement on TinyFace while maintaining performance on high-resolution benchmarks., Comment: 2023 IEEE International Joint Conference on Biometrics (IJCB)

In this paper, we present a new multi-branch neural network that simultaneously performs soft biometric (SB) prediction as an auxiliary modality and face recognition (FR) as the main task. Our proposed network named AAFace utilizes SB attributes to enhance the discriminative ability of FR representation. To achieve this goal, we propose an attribute-aware attentional integration (AAI) module to perform weighted integration of FR with SB feature maps. Our proposed AAI module is not only fully context-aware but also capable of learning complex relationships between input features by means of the sequential multi-scale channel and spatial sub-modules. Experimental results verify the superiority of our proposed network compared with the state-of-the-art (SoTA) SB prediction and FR methods., Comment: Accepted to $30^{th}$ IEEE International Conference on Image Processing (ICIP 2023) as an oral presentation

The design of a neural image compression network is governed by how well the entropy model matches the true distribution of the latent code. Apart from the model capacity, this ability is indirectly under the effect of how close the relaxed quantization is to the actual hard quantization. Optimizing the parameters of a rate-distortion variational autoencoder (R-D VAE) is ruled by this approximated quantization scheme. In this paper, we propose a feature-level frequency disentanglement to help the relaxed scalar quantization achieve lower bit rates by guiding the high entropy latent features to include most of the low-frequency texture of the image. In addition, to strengthen the de-correlating power of the transformer-based analysis/synthesis transform, an augmented self-attention score calculation based on the Hadamard product is utilized during both encoding and decoding. Channel-wise autoregressive entropy modeling takes advantage of the proposed frequency separation as it inherently directs high-informational low-frequency channels to the first chunks and conditions the future chunks on it. The proposed network not only outperforms hand-engineered codecs, but also neural network-based codecs built on computation-heavy spatially autoregressive entropy models., Comment: Accepted to 30$^{th}$ IEEE International Conference on Image Processing (ICIP 2023)

Currently available face datasets mainly consist of a large number of high-quality and a small number of low-quality samples. As a result, a Face Recognition (FR) network fails to learn the distribution of low-quality samples since they are less frequent during training (underrepresented). Moreover, current state-of-the-art FR training paradigms are based on the sample-to-center comparison (i.e., Softmax-based classifier), which results in a lack of uniformity between train and test metrics. This work integrates a quality-aware learning process at the sample level into the classification training paradigm (QAFace). In this regard, Softmax centers are adaptively guided to pay more attention to low-quality samples by using a quality-aware function. Accordingly, QAFace adds a quality-based adjustment to the updating procedure of the Softmax-based classifier to improve the performance on the underrepresented low-quality samples. Our method adaptively finds and assigns more attention to the recognizable low-quality samples in the training datasets. In addition, QAFace ignores the unrecognizable low-quality samples using the feature magnitude as a proxy for quality. As a result, QAFace prevents class centers from getting distracted from the optimal direction. The proposed method is superior to the state-of-the-art algorithms in extensive experimental results on the CFP-FP, LFW, CPLFW, CALFW, AgeDB, IJB-B, and IJB-C datasets., Comment: IEEE/CVF Winter Conference on Applications of Computer Vision (WACV23)

Non-fullerene acceptors (NFA) have delivered advance in bulk heterojunction organic solar cell efficiencies, with the significant milestone of 20% now in sight. However, these materials challenge the accepted wisdom of how organic solar cells work. In this work we present neat Y6 device with efficiency above 4.5%. We thoroughly investigate mechanisms of charge generation and recombination as well as transport in order to understand what is special about Y6. Our data suggest Y6 generates bulk free charges, with ambipolar mobility, which can be extracted in the presence of transport layers, Comment: 11 pages, 5 figures

In recent years, face recognition systems have achieved exceptional success due to promising advances in deep learning architectures. However, they still fail to achieve expected accuracy when matching profile images against a gallery of frontal images. Current approaches either perform pose normalization (i.e., frontalization) or disentangle pose information for face recognition. We instead propose a new approach to utilize pose as an auxiliary information via an attention mechanism. In this paper, we hypothesize that pose attended information using an attention mechanism can guide contextual and distinctive feature extraction from profile faces, which further benefits a better representation learning in an embedded domain. To achieve this, first, we design a unified coupled profile-to-frontal face recognition network. It learns the mapping from faces to a compact embedding subspace via a class-specific contrastive loss. Second, we develop a novel pose attention block (PAB) to specially guide the pose-agnostic feature extraction from profile faces. To be more specific, PAB is designed to explicitly help the network to focus on important features along both channel and spatial dimension while learning discriminative yet pose invariant features in an embedding subspace. To validate the effectiveness of our proposed method, we conduct experiments on both controlled and in the wild benchmarks including Multi-PIE, CFP, IJBC, and show superiority over the state of the arts., Comment: 10 pages, 5 figures, Accepted at IJCB, 2022

In this paper, we seek to draw connections between the frontal and profile face images in an abstract embedding space. We exploit this connection using a coupled-encoder network to project frontal/profile face images into a common latent embedding space. The proposed model forces the similarity of representations in the embedding space by maximizing the mutual information between two views of the face. The proposed coupled-encoder benefits from three contributions for matching faces with extreme pose disparities. First, we leverage our pose-aware contrastive learning to maximize the mutual information between frontal and profile representations of identities. Second, a memory buffer, which consists of latent representations accumulated over past iterations, is integrated into the model so it can refer to relatively much more instances than the mini-batch size. Third, a novel pose-aware adversarial domain adaptation method forces the model to learn an asymmetric mapping from profile to frontal representation. In our framework, the coupled-encoder learns to enlarge the margin between the distribution of genuine and imposter faces, which results in high mutual information between different views of the same identity. The effectiveness of the proposed model is investigated through extensive experiments, evaluations, and ablation studies on four benchmark datasets, and comparison with the compelling state-of-the-art algorithms., Comment: INTERNATIONAL JOINT CONFERENCE ON BIOMETRICS (IJCB 2022)

Finding stimuli capable of driving an imbalance of spin-polarised electrons within a solid is the central challenge in the development of spintronic devices. However, without the aid of magnetism, routes towards this goal are highly constrained with only a few suitable pairings of compounds and driving mechanisms found to date. Here, through spin- and angle-resolved photoemission along with density functional theory, we establish how the $p$-derived bulk valence bands of semiconducting 1T-HfSe$_2$ possess a local, ground-state spin texture spatially confined within each Se-sublayer due to strong sublayer-localised electric dipoles orientated along the $c$-axis. This hidden spin-polarisation manifests in a `coupled spin-orbital texture' with in-equivalent contributions from the constituent $p$-orbitals. While the overall spin-orbital texture for each Se sublayer is in strict adherence to time-reversal symmetry (TRS), spin-orbital mixing terms with net polarisations at time-reversal invariant momenta are locally maintained. These apparent TRS-breaking contributions dominate, and can be selectively tuned between with a choice of linear light polarisation, facilitating the observation of pronounced spin-polarisations at the Brillouin zone centre for all $k_z$. We discuss the implications for the generation of spin-polarised populations from 1T-structured transition metal dichalcogenides using a fixed energy, linearly polarised light source., Comment: 11 pages, 6 figures

According to UNICEF, pneumonia is the leading cause of death in children under 5. 70% of worldwide pneumonia deaths occur in only 15 countries, including Bangladesh. Previous research has indicated a potential association between the incidence of pneumonia and the presence of cross-ventilation in slum housing in Dhaka, Bangladesh. The objective of this research is to establish a validated computational framework that can predict ventilation rates in slum homes to support further studies investigating this correlation. To achieve this objective we employ a building thermal model (BTM) in combination with uncertainty quantification (UQ). The BTM solves for the time-evolution of volume-averaged temperatures in a typical home, considering different ventilation configurations. The UQ method propagates uncertainty in model parameters, weather inputs, and physics models to predict mean values and 95% confidence intervals for the quantities of interest, namely temperatures and ventilation rates in terms of air changes per hour (ACH). The model predictions are compared to on-site field measurements of air and thermal mass temperatures, and of ACH. The results indicate that the use of standard cross- or single-sided ventilation models limits the accuracy of the ACH predictions; in contrast, a model based on a similarity relationship informed by the available ACH measurements can produce more accurate predictions with confidence intervals that encompass the measurements for 12 of the 17 available data points.

Multimodal data provide complementary information of a natural phenomenon by integrating data from various domains with very different statistical properties. Capturing the intra-modality and cross-modality information of multimodal data is the essential capability of multimodal learning methods. The geometry-aware data analysis approaches provide these capabilities by implicitly representing data in various modalities based on their geometric underlying structures. Also, in many applications, data are explicitly defined on an intrinsic geometric structure. Generalizing deep learning methods to the non-Euclidean domains is an emerging research field, which has recently been investigated in many studies. Most of those popular methods are developed for unimodal data. In this paper, a multimodal multi-scaled graph wavelet convolutional network (M-GWCN) is proposed as an end-to-end network. M-GWCN simultaneously finds intra-modality representation by applying the multiscale graph wavelet transform to provide helpful localization properties in the graph domain of each modality, and cross-modality representation by learning permutations that encode correlations among various modalities. M-GWCN is not limited to either the homogeneous modalities with the same number of data, or any prior knowledge indicating correspondences between modalities. Several semi-supervised node classification experiments have been conducted on three popular unimodal explicit graph-based datasets and five multimodal implicit ones. The experimental results indicate the superiority and effectiveness of the proposed methods compared with both spectral graph domain convolutional neural networks and state-of-the-art multimodal methods., Comment: 13 pages