WavNet — Visual saliency detection using Discrete Wavelet Convolutional Neural Network

In the recent advancements in image and video analysis, the detection of salient regions in the image becomes the initial step. This plays a crucial role in deciding the performance of such algorithms. In this work, a Multi-Resolution Feature Extraction (MRFE) technique that makes use of Discrete Wavelet Convolutional Neural Network (DWCNN) for generating features is employed. An Enhanced Feature Extraction (EFE) module extracts additional features from the high level features of the DWCNN, which are used to frame both channel as well as spatial attention models for yielding contextual attention maps. A new hybrid loss function is also proposed, which is a combination of Balanced Cross Entropy (BCE) loss and Edge based Structural Similarity (ESSIM) loss that effectively identifies and segments the salient regions with clear boundaries. The method is tested exhaustively with five different benchmark datasets and is proved superior to the existing state-of-the-art methods with a minimum Mean Absolute error (MAE) of 0.03 and F-measure of 0.956.     

Optimized microwave absorption properties by tailoring the morphology of carbon coated TiC nanoparticles by N2 pressure

Increasing the dielectric loss capacity plays an important role in enhancing the electromagnetic absorption performance of materials. It remains a challenge to simultaneously introduce multiple types of dielectric losses in the material. In this work, we show that the atomic and interfacial dipole polarizations can be simultaneously enhanced by substituting N species into both carbon coating layers and bulk TiC lattices of a core-shell TiC@C material. Additionally, substitution of N species results more exposed TiC(111) facets and refines the TiC grain sizes in the bulk material, which is beneficial for enhancing the scattering of the external electromagnetic waves. The maximum reflection loss of the N substituted TiC@C material is measured as ?47.1 dB with an effective absorbing bandwidth of 4.83 GHz at 1.9 mm, which illustrates a valuable way to further tuning the electromagnetic absorption performance of this type of materials.     

Nonlinear dielectric response and positive dielectric tunability in antipolar CaTiSiO5

Dielectric tunability has been extensively investigated in ferroelectric materials, which exhibit a negative tunability of dielectric permittivity in an external electric field. In contrast, positive tunability is rare and has been reported only in a few antiferroelectric materials. We present positive (and negative) tunability in the titanite, CaTiSiO₅. The dielectric property of CaTiSiO₅ was measured up to an extraordinarily high electric field of 40 MV/m. A nonlinear polarization field loop with no hysteresis was obtained. The dielectric permittivity of ε_r ~ 25 increases up to ε_r ~ 40 at 20 MV/m and room temperature. Although titanite has an antipolar structure and is expected to be “antiferroelectric,” its dielectric response in high electric fields up to ~40 MV/m differs from that of conventional antiferroelectrics. We demonstrate that the phase-transition temperature and dielectric tunability could be modulated through the chemical substitution of Ca_1−xLa_xTiSi_1−xAl_xO₅, in which the destabilization of the long-range antipolar order is revealed by transmission electron microscopy analysis. These results indicate that the observed dielectric response to an electric field may originate from the unique features of the antipolar and domain structures in CaTiSiO₅.     

Theoretical estimation of dielectric loss of oxide glasses using nonequilibrium molecular dynamics simulations

To theoretically explore amorphous materials with a sufficiently low dielectric loss, which are essential for next-generation communication devices, the applicability of a nonequilibrium molecular dynamics simulation employing an external alternating electric field was examined using alkaline silicate glass models. In this method, the dielectric loss is directly evaluated as the phase shift of the dipole moment from the applied electric field. This method enabled us to evaluate the dielectric loss in a wide frequency range from 1 GHz to 10 THz. It was observed that the dielectric loss reaches its maximum at a few THz. The simulation method was found to qualitatively reproduce the effects of alkaline content and alkaline type on the dielectric loss. Furthermore, it reasonably reproduced the effect of mixed alkalines on the dielectric loss, which was observed in our experiments on sodium and/or potassium silicate glasses. Alkaline mixing was thus found to reduce the dielectric loss.     

Microstructure,phase, magnetic properties,and electromagnetic wave absorption of graphene oxide – Ni0.7Zn0.3Fe2O4 – Al2O3 aerogel

In this work, an ultralight nanocomposite of graphene oxide aerogels as a matrix and nickel-zinc ferrite (Ni_0.7Zn_0.3Fe₂O₄) nanoparticles as a second phase for the absorption of electromagnetic waves in the frequency of 1–18 GHz were fabricated by the hydrothermal - freeze-drying method. α-Al₂O₃ nanoparticles were used for further impedance matching for applications in electromagnetic wave absorption. XRD, SEM, EDS, and VNA analyses were used to characterize the sample. The effects of the amount of Ni_0.7Zn_0.3Fe₂O₄ (NZF) nanoparticles (GO: NZF volume percent ratio = 5:1 and 2:1) on the absorption of electromagnetic waves were investigated.     

Retinal microaneurysms detection using adversarial pre-training with unlabeled multimodal images

The detection of retinal microaneurysms is crucial for the early detection of important diseases such as diabetic retinopathy. However, the detection of these lesions in retinography, the most widely available retinal imaging modality, remains a very challenging task. This is mainly due to the tiny size and low contrast of the microaneurysms in the images. Consequently, the automated detection of microaneurysms usually relies on extensive ad-hoc processing. In this regard, although microaneurysms can be more easily detected using fluorescein angiography, this alternative imaging modality is invasive and not adequate for regular preventive screening.In this work, we propose a novel deep learning methodology that takes advantage of unlabeled multimodal image pairs for improving the detection of microaneurysms in retinography. In particular, we propose a novel adversarial multimodal pre-training consisting in the prediction of fluorescein angiography from retinography using generative adversarial networks. This pre-training allows learning about the retina and the microaneurysms without any manually annotated data. Additionally, we also propose to approach the microaneurysms detection as a heatmap regression, which allows an efficient detection and precise localization of multiple microaneurysms. To validate and analyze the proposed methodology, we perform an exhaustive experimentation on different public datasets. Additionally, we provide relevant comparisons against different state-of-the-art approaches. The results show a satisfactory performance of the proposal, achieving an Average Precision of 64.90%, 31.36%, and 33.55% in the E-Ophtha, ROC, and DDR public datasets. Overall, the proposed approach outperforms existing deep learning alternatives while providing a more straightforward detection method that can be effectively applied to raw unprocessed retinal images.     

Effect of heat loss on the syngas production by fuel-rich combustion in a divergent two-layer burner

The effect of heat loss on the syngas production from partial combustion of fuel-rich in a divergent two-layer burner is numerically studied using two-dimensional model with detailed kinetics GRI-Mech 1.2. Both the radiation and wall heat losses to the surrounding are considered in the computations. It is shown that two types heat losses have different effects on the syngas production. The radiation heat loss has significant effect on the syngas temperature and the syngas temperature is dropped as radiation heat loss is increased, but it has neglected effect on the reforming efficiency and methane conversion efficiency. The wall heat loss has a comprehensive effect on the syngas production. The wall heat loss not only reduces the conversion efficiency, but also significantly decreases the syngas temperature. The effect of wall heat loss becomes weak as the equivalence is increased. The reforming efficiency drops from 0.440 to 0.424 for equivalence ratio of 2 and mixture velocity of 0.17 m/s for the predictions between adiabatic wall and non-adiabatic conditions.     

A Lane-Level Road Marking Map Using a Monocular Camera

The essential requirement for precise localization of a self-driving car is a lane-level map which includes road markings (RMs). Obviously, we can build the lane-level map by running a mobile mapping system (MMS) which is equipped with a high-end 3D LiDAR and a number of high-cost sensors. This approach, however, is highly expensive and ineffective since a single high-end MMS must visit every place for mapping. In this paper, a lane-level RM mapping system using a monocular camera is developed. The developed system can be considered as an alternative to expensive high-end MMS. The developed RM map includes the information of road lanes (RLs) and symbolic road markings (SRMs). First, to build a lane-level RM map, the RMs are segmented at pixel level through the deep learning network. The network is named RMNet. The segmented RMs are then gathered to build a lane-level RM map. Second, the lane-level map is improved through loop-closure detection and graph optimization. To train the RMNet and build a lane-level RM map, a new dataset named SeRM set is developed. The set is a large dataset for lane-level RM mapping and it includes a total of 25157 pixel-wise annotated images and 21000 position labeled images. Finally, the proposed lane-level map building method is applied to SeRM set and its validity is demonstrated through experimentation.      

Mutual information maximizing GAN inversion for real face with identity preservation

Recent generative adversarial networks (GANs) have yielded remarkable performance in face image synthesis. GAN inversion embeds an image into the latent space of a pretrained generator, enabling it to be used for real face manipulation. However, current inversion approaches for real faces suffer the dilemma of initialization collapse and identity loss. In this paper, we propose a hierarchical GAN inversion for real faces with identity preservation based on mutual information maximization. We first use a facial domain guaranteed initialization to avoid the initialization collapse. Furthermore, we prove that maximizing the mutual information between inverted faces and their identities is equivalent to minimizing the distance between identity features from inverted and original faces. Optimization for real face inversion with identity preservation is implemented on this mutual information-maximizing constraint. Extensive experimental results show that our approach outperforms state-of-the-art solutions for inverting and editing real faces, particularly in terms of face identity preservation.