The Position Embedding (PE) is critical for Vision Transformers (VTs) due to the permutation-invariance of self-attention operation. By analyzing the input and output of each encoder layer in VTs using reparameterization and visualization, we find that the default PE joining method (simply adding the PE and patch embedding together) operates the same affine transformation to token embedding and PE, which limits the expressiveness of PE and hence constrains the performance of VTs. To overcome this limitation, we propose a simple, effective, and robust method. Specifically, we provide two independent layer normalizations for token embeddings and PE for each layer, and add them together as the input of each layer's Muti-Head Self-Attention module. Since the method allows the model to adaptively adjust the information of PE for different layers, we name it as Layer-adaptive Position Embedding, abbreviated as LaPE. Extensive experiments demonstrate that LaPE can improve various VTs with different types of PE and make VTs robust to PE types. For example, LaPE improves 0.94% accuracy for ViT-Lite on Cifar10, 0.98% for CCT on Cifar100, and 1.72% for DeiT on ImageNet-1K, which is remarkable considering the negligible extra parameters, memory and computational cost brought by LaPE. The code is publicly available at https://github.com/Ingrid725/LaPE.
Smart and unobtrusive mobile sensor nodes that accurately track their own position have the potential to augment data collection with location-based functions. To attain this vision of unobtrusiveness, the sensor nodes must have a compact form factor and operate over long periods without battery recharging or replacement. This paper presents a self-sustaining and accurate ultra-wideband-based indoor location system with conservative infrastructure overhead. An event-driven sensing approach allows for balancing the limited energy harvested in indoor conditions with the power consumption of ultra-wideband transceivers. The presented tag-centralized concept, which combines heterogeneous system design with embedded processing, minimizes idle consumption without sacrificing functionality. Despite modest infrastructure requirements, high localization accuracy is achieved with error-correcting double-sided two-way ranging and embedded optimal multilateration. Experimental results demonstrate the benefits of the proposed system: the node achieves a quiescent current of $47~nA$ and operates at $1.2~\mu A$ while performing energy harvesting and motion detection. The energy consumption for position updates, with an accuracy of $40~cm$ (2D) in realistic non-line-of-sight conditions, is $10.84~mJ$. In an asset tracking case study within a $200~m^2$ multi-room office space, the achieved accuracy level allows for identifying 36 different desk and storage locations with an accuracy of over $95~{\%}$. The system`s long-time self-sustainability has been analyzed over $700~days$ in multiple indoor lighting situations.
We consider the problem of direction finding using partly calibrated arrays, a distributed subarray with position errors between subarrays. The key challenge is to enhance angular resolution in the presence of position errors. To achieve this goal, existing algorithms, such as subspace separation and sparse recovery, have to rely on multiple snapshots, which increases the burden of data transmission and the processing delay. Therefore, we aim to enhance angular resolution using only a single snapshot. To this end, we exploit the orthogonality of the signals of partly calibrated arrays. Particularly, we transform the signal model into a special multiple-measurement model, show that there is approximate orthogonality between the source signals in this model, and then use blind source separation to exploit the orthogonality. Simulation and experiment results both verify that our proposed algorithm achieves high angular resolution as distributed arrays without position errors, inversely proportional to the whole array aperture.
A recent perspective paper by Kazanina & Tavano (referred to as the KT perspective in the following) argues how neural oscillations cannot provide a potential neural correlate for syntactic structure building. The view that neural oscillations can provide a potential neural correlate for syntactic structure building is largely attributed to a study by Ding, Melloni, Zhang, Tian, and Poeppel in 2016 (referred to as the DMZTP study). The KT perspective is thought provoking, but has severe misinterpretations about the arguments in DMZTP and other studies, and contains contradictory conclusions in different parts of the perspective, making it impossible to understand the position of the authors. In the following, I summarize a few misinterpretations and inconsistent arguments in the KT perspective, and put forward a few suggestions for future studies.
Obtaining the position of ego-vehicle is a crucial prerequisite for automatic control and path planning in the field of autonomous driving. Most existing positioning systems rely on GPS, RTK, or wireless signals, which are arduous to provide effective localization under weak signal conditions. This paper proposes a real-time positioning system based on the detection of the parking numbers as they are unique positioning marks in the parking lot scene. It does not only can help with the positioning with open area, but also run independently under isolation environment. The result tested on both public datasets and self-collected dataset show that the system outperforms others in both performances and applies in practice. In addition, the code and dataset will release later.
Attention-based arbitrary style transfer studies have shown promising performance in synthesizing vivid local style details. They typically use the all-to-all attention mechanism -- each position of content features is fully matched to all positions of style features. However, all-to-all attention tends to generate distorted style patterns and has quadratic complexity, limiting the effectiveness and efficiency of arbitrary style transfer. In this paper, we propose a novel all-to-key attention mechanism -- each position of content features is matched to stable key positions of style features -- that is more in line with the characteristics of style transfer. Specifically, it integrates two newly proposed attention forms: distributed and progressive attention. Distributed attention assigns attention to key style representations that depict the style distribution of local regions; Progressive attention pays attention from coarse-grained regions to fine-grained key positions. The resultant module, dubbed StyA2K, shows extraordinary performance in preserving the semantic structure and rendering consistent style patterns. Qualitative and quantitative comparisons with state-of-the-art methods demonstrate the superior performance of our approach.
Crowd localization aims to predict the spatial position of humans in a crowd scenario. We observe that the performance of existing methods is challenged from two aspects: (i) ranking inconsistency between test and training phases; and (ii) fixed anchor resolution may underfit or overfit crowd densities of local regions. To address these problems, we design a supervision target reassignment strategy for training to reduce ranking inconsistency and propose an anchor pyramid scheme to adaptively determine the anchor density in each image region. Extensive experimental results on three widely adopted datasets (ShanghaiTech A\&B, JHU-CROWD++, UCF-QNRF) demonstrate the favorable performance against several state-of-the-art methods.
This paper proposes a Learnable Multiplicative absolute position Embedding based Conformer (LMEC). It contains a kernelized linear attention (LA) module called LMLA to solve the time-consuming problem for long sequence speech recognition as well as an alternative to the FFN structure. First, the ELU function is adopted as the kernel function of our proposed LA module. Second, we propose a novel Learnable Multiplicative Absolute Position Embedding (LM-APE) based re-weighting mechanism that can reduce the well-known quadratic temporal-space complexity of softmax self-attention. Third, we use Gated Linear Units (GLU) to substitute the Feed Forward Network (FFN) for better performance. Extensive experiments have been conducted on the public LibriSpeech datasets. Compared to the Conformer model with cosFormer style linear attention, our proposed method can achieve up to 0.63% word-error-rate improvement on test-other and improve the inference speed by up to 13% (left product) and 33% (right product) on the LA module.
Motivation: Enhancers are important cis-regulatory elements that regulate a wide range of biological functions and enhance the transcription of target genes. Although many feature extraction methods have been proposed to improve the performance of enhancer identification, they cannot learn position-related multiscale contextual information from raw DNA sequences. Results: In this article, we propose a novel enhancer identification method (iEnhancer-ELM) based on BERT-like enhancer language models. iEnhancer-ELM tokenizes DNA sequences with multi-scale k-mers and extracts contextual information of different scale k-mers related with their positions via an multi-head attention mechanism. We first evaluate the performance of different scale k-mers, then ensemble them to improve the performance of enhancer identification. The experimental results on two popular benchmark datasets show that our model outperforms stateof-the-art methods. We further illustrate the interpretability of iEnhancer-ELM. For a case study, we discover 30 enhancer motifs via a 3-mer-based model, where 12 of motifs are verified by STREME and JASPAR, demonstrating our model has a potential ability to unveil the biological mechanism of enhancer. Availability and implementation: The models and associated code are available at https://github.com/chen-bioinfo/iEnhancer-ELM Contact: [email omitted] Supplementary information: Supplementary data are available at Bioinformatics Advances online.
Graph generative models have broad applications in biology, chemistry and social science. However, modelling and understanding the generative process of graphs is challenging due to the discrete and high-dimensional nature of graphs, as well as permutation invariance to node orderings in underlying graph distributions. Current leading autoregressive models fail to capture the permutation invariance nature of graphs for the reliance on generation ordering and have high time complexity. Here, we propose a continuous-time generative diffusion process for permutation invariant graph generation to mitigate these issues. Specifically, we first construct a forward diffusion process defined by a stochastic differential equation (SDE), which smoothly converts graphs within the complex distribution to random graphs that follow a known edge probability. Solving the corresponding reverse-time SDE, graphs can be generated from newly sampled random graphs. To facilitate the reverse-time SDE, we newly design a position-enhanced graph score network, capturing the evolving structure and position information from perturbed graphs for permutation equivariant score estimation. Under the evaluation of comprehensive metrics, our proposed generative diffusion process achieves competitive performance in graph distribution learning. Experimental results also show that GraphGDP can generate high-quality graphs in only 24 function evaluations, much faster than previous autoregressive models.
The increase in the number of unmanned aerial vehicles a.k.a. drones pose several threats to public privacy, critical infrastructure and cyber security. Hence, detecting unauthorized drones is a significant problem which received attention in the last few years. In this paper, we present our experimental work on three drone detection methods (i.e., acoustic detection, radio frequency (RF) detection, and visual detection) to evaluate their efficacy in both indoor and outdoor environments. Owing to the limitations of these schemes, we present a novel encryption-based drone detection scheme that uses a two-stage verification of the drone's received signal strength indicator (RSSI) and the encryption key generated from the drone's position coordinates to reliably detect an unauthorized drone in the presence of authorized drones.
Reluctance actuators are preferred for high-precision applications. Due to resistive losses in the coils, the accuracy of this type of actuator will reduce in quasi-static operation mode within a vacuum environment. By using soft permanent magnets whose magnetization states are in-situ tuned, no constant power is needed to create a force and thereby the resistive losses will reduce. In this paper, a new tuning method is investigated in order to reduce the resistive losses. By using a history-dependent and non-linear hysteresis model, a more efficient tuning algorithm is designed. Besides this, the position accuracy and control simplicity of a variable reluctance tunable magnet actuator are improved by linearizing the non-linear force-flux relationship. This is achieved by using bias fluxes generated by hard permanent magnets.
This paper deals with dynamic Blind Source Extraction (BSE) from where the mixing parameters characterizing the position of a source of interest (SOI) are allowed to vary over time. We present a new source extraction model called CvxCSV which is a parameter-reduced modification of the recent Constant Separation Vector (CSV) mixing model. In CvxCSV, the mixing vector evolves as a convex combination of its initial and final values. We derive a lower bound on the achievable mean interference-to-signal ratio (ISR) based on the Cram\'er-Rao theory. The bound reveals advantageous properties of CvxCSV compared with CSV and compared with a sequential BSE based on independent component extraction (ICE). In particular, the achievable ISR by CvxCSV is lower than that by the previous approaches. Moreover, the model requires significantly weaker conditions for identifiability, even when the SOI is Gaussian.
The introductory programming sequence has been the focus of much research in computing education. The recent advent of several viable and freely-available AI-driven code generation tools present several immediate opportunities and challenges in this domain. In this position paper we argue that the community needs to act quickly in deciding what possible opportunities can and should be leveraged and how, while also working on how to overcome or otherwise mitigate the possible challenges. Assuming that the effectiveness and proliferation of these tools will continue to progress rapidly, without quick, deliberate, and concerted efforts, educators will lose advantage in helping shape what opportunities come to be, and what challenges will endure. With this paper we aim to seed this discussion within the computing education community.
By a symmetry argument, a synethic aperture radar collection along a linear path does not collect three-dimensional information about the scene. However, it is known that vertical curvature can be used to derive some vertical position information. This paper approaches the problem from a monopulse perspective, resulting in a non-iterative computation that commutes with efficient image formation algorithms.
We present DyFOS, an active perception method that dynamically finds optimal states to minimize localization uncertainty while avoiding obstacles and occlusions. We consider the scenario where a perception-denied rover relies on position and uncertainty measurements from a viewer robot to localize itself along an obstacle-filled path. The position uncertainty from the viewer's sensor is a function of the states of the sensor itself, the rover, and the surrounding environment. To find an optimal sensor state that minimizes the rover's localization uncertainty, DyFOS uses a localization uncertainty prediction pipeline in an optimization search. Given numerous samples of the states mentioned above, the pipeline predicts the rover's localization uncertainty with the help of a trained, complex state-dependent sensor measurement model (a probabilistic neural network). Our pipeline also predicts occlusion and obstacle collision to remove undesirable viewer states and reduce unnecessary computations. We evaluate the proposed method numerically and in simulation. Our results show that DyFOS is faster than brute force yet performs on par. DyFOS also yielded lower localization uncertainties than faster random and heuristic-based searches.
The accurate detection and grasping of transparent objects are challenging but of significance to robots. Here, a visual-tactile fusion framework for transparent object grasping under complex backgrounds and variant light conditions is proposed, including the grasping position detection, tactile calibration, and visual-tactile fusion based classification. First, a multi-scene synthetic grasping dataset generation method with a Gaussian distribution based data annotation is proposed. Besides, a novel grasping network named TGCNN is proposed for grasping position detection, showing good results in both synthetic and real scenes. In tactile calibration, inspired by human grasping, a fully convolutional network based tactile feature extraction method and a central location based adaptive grasping strategy are designed, improving the success rate by 36.7% compared to direct grasping. Furthermore, a visual-tactile fusion method is proposed for transparent objects classification, which improves the classification accuracy by 34%. The proposed framework synergizes the advantages of vision and touch, and greatly improves the grasping efficiency of transparent objects.
Incorporating prior knowledge of physics laws and structural properties of dynamical systems into the design of deep learning architectures has proven to be a powerful technique for improving their computational efficiency and generalization capacity. Learning accurate models of robot dynamics is critical for safe and stable control. Autonomous mobile robots, including wheeled, aerial, and underwater vehicles, can be modeled as controlled Lagrangian or Hamiltonian rigid-body systems evolving on matrix Lie groups. In this paper, we introduce a new structure-preserving deep learning architecture, the Lie group Forced Variational Integrator Network (LieFVIN), capable of learning controlled Lagrangian or Hamiltonian dynamics on Lie groups, either from position-velocity or position-only data. By design, LieFVINs preserve both the Lie group structure on which the dynamics evolve and the symplectic structure underlying the Hamiltonian or Lagrangian systems of interest. The proposed architecture learns surrogate discrete-time flow maps allowing accurate and fast prediction without numerical-integrator, neural-ODE, or adjoint techniques, which are needed for vector fields. Furthermore, the learnt discrete-time dynamics can be utilized with computationally scalable discrete-time (optimal) control strategies.
Over the recent twenty years, argumentation has received considerable attention in the fields of knowledge representation, reasoning, and multi-agent systems. However, argumentation in dynamic multi-agent systems encounters the problem of significant arguments generated by agents, which comes at the expense of representational complexity and computational cost. In this work, we aim to investigate the notion of abstraction from the model-checking perspective, where several arguments are trying to defend the same position from various points of view, thereby reducing the size of the argumentation framework whilst preserving the semantic flow structure in the system.
Recently, large-scale text-to-image (T2I) models have shown impressive performance in generating high-fidelity images, but with limited controllability, e.g., precisely specifying the content in a specific region with a free-form text description. In this paper, we propose an effective technique for such regional control in T2I generation. We augment T2I models' inputs with an extra set of position tokens, which represent the quantized spatial coordinates. Each region is specified by four position tokens to represent the top-left and bottom-right corners, followed by an open-ended natural language regional description. Then, we fine-tune a pre-trained T2I model with such new input interface. Our model, dubbed as ReCo (Region-Controlled T2I), enables the region control for arbitrary objects described by open-ended regional texts rather than by object labels from a constrained category set. Empirically, ReCo achieves better image quality than the T2I model strengthened by positional words (FID: 8.82->7.36, SceneFID: 15.54->6.51 on COCO), together with objects being more accurately placed, amounting to a 20.40% region classification accuracy improvement on COCO. Furthermore, we demonstrate that ReCo can better control the object count, spatial relationship, and region attributes such as color/size, with the free-form regional description. Human evaluation on PaintSkill shows that ReCo is +19.28% and +17.21% more accurate in generating images with correct object count and spatial relationship than the T2I model.