Injective Modules Research Articles

MFFOD: Multidomain Feature Fusion Object Detector for Infrared Images

Abstract Infrared imagery surpasses the limitations of visible light images and finds widespread applications in fields such as military reconnaissance and security surveillance. Recent studies on infrared target detection aim to preserve local features and global representations to the greatest extent. However, compared to visible light images, infrared images exhibit inherent challenges such as insufficient texture information and coarse boundaries, which introduce new difficulties to this research. To address these issues, this paper introduces additional information cues from the perspective of enriching feature map information. Specifically, we propose a multidomain feature fusion object detector (MFFOD), whose backbone feature extraction network consists of a convolutional branch and a fast Fourier transform (FFT) branch. This hybrid domain representation enables the extraction of both domain-specific information and global high-frequency and low-frequency information with minimal computational overhead. Furthermore, in the intermediate layers of the network, we have carefully designed a feature injection module that enables comprehensive interaction between channel features and spatial features within a single feature map. Experimental results demonstrate that MFFOD achieves average detection accuracies of 88.97%, 90.32%, and 99.25% on three significant infrared scene datasets, outperforming existing target detection methods. We hope that this general detection algorithm will provide a robust reference for future infrared target detection research.

Experimental Investigation of Dual-Path Inline Mixing System for Sprayers in Corn-Soybean Strip Intercropping Mode

Corn-soybean strip intercropping, which fully utilizes land resources and has high total yield and soil fertility, has become a modern agricultural cultivation mode that is actively promoted. In order to solve the weed problem in corn-soybean strip intercropping, the agricultural technology requirements cannot be met by traditional pre-mixed spraying machines, so a direct injection dual-path inline mixing system was designed for the corn-soybean strip intercropping mode. The system was integrated to improve its installation convenience and universality, and was capable of fulfilling the requirements for the simultaneous application of two types of pesticides at varying mixing ratios. The system mainly consists of a water solvent injection module, glyphosate (pesticide for corn) inline mixing module, and a fomesafen (soybean pesticide) inline mixing module. First, the detection rules of the mixing ratio of related pesticides based on the electrical conductivity measurement principle were studied. Then, the working characteristics of the designed direct injection dual-path inline mixing system were studied through experiments using different pesticides and mixing ratio adjustment ranges. The mixing uniformity test showed that the designed direct injection dual-path inline mixing system had good mixing uniformity, and the maximum uniformity coefficient of the mixing ratio was 9.7%. The stability test showed that the mixing ratio of the designed dual-path inline mixing system was relatively stable, with the maximum standard deviation of the mixing ratio accounting for about 2.2% of its average value, and the maximum average deviation was less than 1.5%. The precision and response time test showed that the designed dual-path inline mixing system had an average deviation of the mixing ratio of less than 2.7% under the condition of a step signal target mixing ratio, and the response time was a maximum of 3.4 s. The results show that the designed dual-path inline mixing system has good performance, and the research findings provide a reference for the design and optimization of inline mixing systems.

Chaos from a free-running broad-area VCSEL.

We experimentally report on the detection of chaos from a free-running commercial broad-area vertical-cavity surface-emitting laser (VCSEL) without the need for external perturbation such as optical feedback, injection, or current modulation. The evolution of nonlinear dynamics leading to chaotic behavior is studied, and the system's complexity is characterized using chaos titration and correlation dimension. We link the occurrence of chaos with the complex interplay between the spatial laser mode competition and polarization dynamics.

An integrated vibration energy harvesting-storage-injection system based on piezoelectric bistable

Abstract Efficiently capturing energy from environmental vibrations remains a significant challenge in sustainable energy systems. This paper presents a novel integrated vibrational energy harvesting-storage-injection system (VEHSIS) to improve energy capture efficiency. The VEHSIS comprises four main components: an Energy Harvesting Module, an Energy Storage Module, an Energy Injection Module, and a Microcontroller Control Module. The VEHSIS employs a four-magnet piezoelectric bistable structure, which decreases the height of the potential barriers and thus enables efficient energy harvesting at lower vibration amplitudes. The proposed VEHSIS incorporates a dual-capacitor mode to improve the synchronous electric charge extraction (SECE) circuit and further presents a phase-locked loop circuit and a microcontroller control method to precisely control the synchronous switching of the SECE circuit to optimize energy storage and utilization. By improving the voltage pulse perturbation technique and using the microcontroller to monitor the system status in real-time, the system is enabled to maintain high-energy orbital oscillation output under different conditions. Experimental analysis reveals that the VEHSIS improves harvesting efficiency by 3.2 times after energy injection, providing 827.5 μW in dual piezoelectric cantilever beam mode. Compared to classical energy harvesting systems, the VEHSIS offers a spontaneous energy harvesting method and a significant improvement in energy conversion efficiency, providing a new solution for self-powered devices.

$S$-$M$-cyclic submodules and some applications

In this paper, we introduce the notion of $S$-$M$-cyclic submodules, which is a generalization of the notion of $M$-cyclic submodules. Let $M, N$ be right $R$-modules and $S$ be a multiplicatively closed subset of a ring $R$. A submodule $A$ of $N$ is said to be an $S$-$M$-cyclic submodule, if there exist $s\in S$ and $f \in Hom_R(M,N)$ such that $As \subseteq f(M) \subseteq A$. Besides giving many properties of $S$-$M$-cyclic submodules, we generalize some results on $M$-cyclic submodules to $S$-$M$-cyclic submodules. Furthermore, we generalize some properties of principally injective modules and pseudo-principally injective modules to $S$-principally injective modules and $S$-pseudo-principally injective modules, respectively. We study the transfer of this notion to various contexts of these modules.

Designs of Charge-Balanced Edge Termination Structures for 3.3 kV SiC Power Devices Using PN Multi-Epitaxial Layers.

We demonstrated 3.3 kV silicon carbide (SiC) PiN diodes using a trenched ring-assisted junction termination extension (TRA-JTE) with PN multi-epitaxial layers. Multiple P+ rings and width-modulated multiple trenches were utilized to alleviate electric-field crowding at the edges of the junction to quantitively control the effective charge (Qeff) in the termination structures. The TRA-JTE forms with the identical P-type epitaxial layer, which enables high-efficiency hole injection and conductivity modulation. The effects of major design parameters for the TRA-JTE, such as the number of trenches (Ntrench) and depth of trenches (Dtrench), were analyzed to obtain reliable blocking capabilities. Furthermore, the single-zone-JTE (SZ-JTE), ring-assisted-JTE (RA-JTE), and trenched-JTE (T-JTE) were also evaluated for comparative analysis. Our results show that the TRA-JTE exhibited the highest breakdown voltage (BV), exceeding 4.2 kV, and the strongest tolerance against variance in doping concentration for the JTE (NJTE) compared to both the RA-JTE and T-JTE due to the charge-balanced edge termination by multiple P+ rings and trench structures.

Design and application of a disposable insulin dosing container and emergency injection module

Design and application of a disposable insulin dosing container and emergency injection module

Structural Attributes Injection Is Better: Exploring General Approach for Radar Image ATR with a Attribute Alignment Adapter

Nowadays, deep learning techniques are extensively applied in the field of automatic target recognition (ATR) for radar images. However, existing data-driven approaches frequently ignore prior knowledge of the target, leading to a lack of interpretability and poor performance of trained models. To address this issue, we first integrate the knowledge of structural attributes into the training process of an ATR model, providing both category and structural information at the dataset level. Specifically, we propose a Structural Attribute Injection (SAI) module that can be flexibly inserted into any framework constructed based on neural networks for radar image recognition. Our proposed method can encode the structural attributes to provide structural information and category correlation of the target and can further apply the proposed SAI module to map the structural attributes to something high-dimensional and align them with samples, effectively assisting in target recognition. It should be noted that our proposed SAI module can be regarded as a prior feature enhancement method, which means that it can be inserted into all downstream target recognition methods on the same dataset with only a single training session. We evaluated the proposed method using two types of radar image datasets under the conditions of few and sufficient samples. The experimental results demonstrate that our application of our proposed SAI module can significantly improve the recognition accuracy of the baseline models, which is equivalent to the existing state-of-the-art (SOTA) ATR approaches and outperforms the SOTA approaches in terms of resource consumption. Specifically, with the SAI module, our approach can achieve substantial accuracy improvements of 3.48%, 18.22%, 1.52%, and 15.03% over traditional networks in four scenarios while requiring 1/5 of the parameter count and just 1/14 of the FLOPs on average.

TmfimCLIP: Text-Driven Multi-Attribute Face Image Manipulation

Text-to-image conversion has garnered significant research attention, with contemporary methods leveraging the latent space analysis of StyleGAN. However, issues with latent code decoupling, interpretability, and controllability often remain, leading to misaligned image attributes. To address these challenges, we propose a refined approach that segments StyleGAN’s latent code using the Visual Language Model (CLIP). Our method aligns the latent code segments with text embeddings via an image-text alignment module and modulates them through a text injection module. Additionally, we incorporate semantic segmentation loss and mouth loss to constrain operations that affect irrelevant attributes. Compared to previous CLIP-driven techniques, our approach significantly enhances decoupling, interpretability, and controllability. Experiments on the CelebA-HQ and FFHQ datasets validate our model’s efficacy through both qualitative and quantitative comparisons. Our model effectively handles a wide range of style variations, achieving an FID score of 21.15 for facial attributes and an ID metric of 0.88 for hair attributes.

Indecomposable injectives over the Jacobson algebra

Let [Formula: see text] be any field. In this paper, we give a complete list of the indecomposable left injective module over the Jacobson algebra [Formula: see text], i.e. the free associative [Formula: see text]-algebra on two (non-commuting) generators, modulo the single relation [Formula: see text]. This is the natural continuation of the paper of the second two authors with Gene Abrams on the characterization of the injective envelope of the simple modules over [Formula: see text].

Adversarial contrastive representation training with external knowledge injection for zero-shot stance detection

Adversarial contrastive representation training with external knowledge injection for zero-shot stance detection

SIFusion: Lightweight infrared and visible image fusion based on semantic injection.

The objective of image fusion is to integrate complementary features from source images to better cater to the needs of human and machine vision. However, existing image fusion algorithms predominantly focus on enhancing the visual appeal of the fused image for human perception, often neglecting their impact on subsequent high-level visual tasks, particularly the processing of semantic information. Moreover, these fusion methods that incorporate downstream tasks tend to be overly complex and computationally intensive, which is not conducive to practical applications. To address these issues, a lightweight infrared and visible light image fusion method known as SIFusion, which is based on semantic injection, is proposed in this paper. This method employs a semantic-aware branch to extract semantic feature information, and then integrates these features into the fused features through a Semantic Injection Module (SIM) to meet the semantic requirements of high-level visual tasks. Furthermore, to simplify the complexity of the fusion network, this method introduces an Edge Convolution Module (ECB) based on structural reparameterization technology to enhance the representational capacity of the encoder and decoder. Extensive experimental comparisons demonstrate that the proposed method performs excellently in terms of visual appeal and advanced semantics, providing satisfactory fusion results for subsequent high-level visual tasks even in challenging scenarios.

Characteristic modules and Gorenstein (co-)homological dimension of groups

Characteristic modules and Gorenstein (co-)homological dimension of groups

ESFuse: Weak Edge Structure Perception Network for Infrared and Visible Image Fusion

Infrared and visible image fusion (IVIF) fully integrates the complementary features of different modal images, and the fused image provides a more comprehensive and objective interpretation of the scene compared to each source image, thus attracting extensive attention in the field of computer vision in recent years. However, current fusion methods usually center their attention on the extraction of prominent features, falling short of adequately safeguarding subtle and diminutive structures. To address this problem, we propose an end-to-end unsupervised IVIF method (ESFuse), which effectively enhances fine edges and small structures. In particular, we introduce a two-branch head interpreter to extract features from source images of different modalities. Subsequently, these features are fed into the edge refinement module with the detail injection module (DIM) to obtain the edge detection results of the source image, improving the network’s ability to capture and retain complex details as well as global information. Finally, we implemented a multiscale feature reconstruction module to obtain the final fusion results by combining the output of the DIM with the output of the head interpreter. Extensive IVIF fusion experiments on existing publicly available datasets show that the proposed ESFuse outperforms the state-of-the-art(SOTA) methods in both subjective vision and objective evaluation, and our fusion results perform well in semantic segmentation, target detection, pose estimation and depth estimation tasks. The source code has been availabled.

Triviality criteria for unbounded complexes

Triviality criteria for unbounded complexes

Lightweight rail surface defect detection algorithm based on an improved YOLOv8

Lightweight rail surface defect detection algorithm based on an improved YOLOv8

N-weak injective and n-weak flat modules under m-semidualizing bimodules

Let [Formula: see text] and [Formula: see text] be rings, the [Formula: see text] two non-negative integers and [Formula: see text] an (faithfully) [Formula: see text]-semidualizing bimodule. In this paper, we introduce, via special super finitely presented module [Formula: see text] with respect [Formula: see text], the concepts of [Formula: see text]-[Formula: see text]-weak injective and [Formula: see text]-[Formula: see text]-weak flat modules, and then we obtain some characterizations of two classes of these modules, namely [Formula: see text] and [Formula: see text] which are larger than that of [Formula: see text]-weak injective and [Formula: see text]-weak flat modules, respectively. Also, we investigate Foxby equivalence relative to these modules. Then over any arbitrary ring, we show some nice properties from the classes [Formula: see text] and [Formula: see text].

On the Baer–Kaplansky theorem for injective modules

On the Baer–Kaplansky theorem for injective modules

Relative injective modules, superstability and noetherian categories

We study classes of modules closed under direct sums, [Formula: see text]-submodules and [Formula: see text]-epimorphic images where [Formula: see text] is either the class of embeddings, RD-embeddings or pure embeddings. We show that the [Formula: see text]-injective modules of theses classes satisfy a Baer-like criterion. In particular, injective modules, RD-injective modules, pure injective modules, flat cotorsion modules and [Formula: see text]-torsion pure injective modules satisfy this criterion. The argument presented is a model theoretic one. We use in an essential way stable independence relations which generalize Shelah’s non-forking to abstract elementary classes. We show that the classical model theoretic notion of superstability is equivalent to the algebraic notion of a noetherian category for these classes. We use this equivalence to characterize noetherian rings, pure semisimple rings, perfect rings and finite products of finite rings and artinian valuation rings via superstability.

ASIFusion: An Adaptive Saliency Injection-Based Infrared and Visible Image Fusion Network

The purpose of infrared and visible image fusion (IVIF) is to acquire a more informative fused image by leveraging complementary information, facilitating human perception and machine vision. Among the existing fusion methods, the saliency-based methods conform to human perception characteristics and achieve relatively advantageous fusion performance. However, such methods fail to adaptively maintain the edge and intensity of salient objects, resulting in fixed fusion performance. To address these issue, we present ASIFusion, an adaptive saliency injection-based IVIF network. First, source images are inputted to the feature extraction encoder for fully extracting features. Meanwhile, the proposed adaptive saliency injection module detects salient objects in the infrared image and then learns the fusion weights of each channel, which serve as supplementary information for further fusion. These learned weights are utilized to merge the source images’ extracted features. Finally, the feature reconstruction decoder produces a fused image with injected saliency. The fused image maintains the intensity and edge of the salient objects and fully preserves the complementary information. Extensive experiments demonstrate that our proposed network outperforms state-of-the-art (SOTA) approaches with regard to fusion performance and computational efficiency.