This paper extends boolean particle swarm optimization to a multi-objective setting, to our knowledge for the first time in the literature. Our proposed new boolean algorithm, MBOnvPSO, is notably simplified by the omission of a velocity update rule and has enhanced exploration ability due to the inclusion of a 'noise' term in the position update rule that prevents particles being trapped in local optima. Our algorithm additionally makes use of an external archive to store non-dominated solutions and implements crowding distance to encourage solution diversity. In benchmark tests, MBOnvPSO produced high quality Pareto fronts, when compared to benchmarked alternatives, for all of the multi-objective test functions considered, with competitive performance in search spaces with up to 600 discrete dimensions.
Questions regarding implicitness, ambiguity and underspecification are crucial for understanding the task validity and ethical concerns of multimodal image+text systems, yet have received little attention to date. This position paper maps out a conceptual framework to address this gap, focusing on systems which generate images depicting scenes from scene descriptions. In doing so, we account for how texts and images convey meaning differently. We outline a set of core challenges concerning textual and visual ambiguity, as well as risks that may be amplified by ambiguous and underspecified elements. We propose and discuss strategies for addressing these challenges, including generating visually ambiguous images, and generating a set of diverse images.
In this paper, we obtain a duality result for the exponential utility maximization problem where trading is subject to quadratic transaction costs and the investor is required to liquidate her position at the maturity date. As an application of the duality, we treat utility-based hedging in the Bachelier model. For European contingent claims with a quadratic payoff, we compute explicitly the optimal trading strategy.
As a pioneering work exploring transformer architecture for 3D point cloud understanding, Point Transformer achieves impressive results on multiple highly competitive benchmarks. In this work, we analyze the limitations of the Point Transformer and propose our powerful and efficient Point Transformer V2 model with novel designs that overcome the limitations of previous work. In particular, we first propose group vector attention, which is more effective than the previous version of vector attention. Inheriting the advantages of both learnable weight encoding and multi-head attention, we present a highly effective implementation of grouped vector attention with a novel grouped weight encoding layer. We also strengthen the position information for attention by an additional position encoding multiplier. Furthermore, we design novel and lightweight partition-based pooling methods which enable better spatial alignment and more efficient sampling. Extensive experiments show that our model achieves better performance than its predecessor and achieves state-of-the-art on several challenging 3D point cloud understanding benchmarks, including 3D point cloud segmentation on ScanNet v2 and S3DIS and 3D point cloud classification on ModelNet40. Our code will be available at https://github.com/Gofinge/PointTransformerV2.
Human pose estimation (HPE) for 3D skeleton reconstruction in telemedicine has long received attention. Although the development of deep learning has made HPE methods in telemedicine simpler and easier to use, addressing low accuracy and high latency remains a big challenge. In this paper, we propose a novel multi-view Attention Cube Regression Network (ACRNet), which regresses the 3D position of joints in real time by aggregating informative attention points on each cube surface. More specially, a cube whose each surface contains uniformly distributed attention points with specific coordinate values is first created to wrap the target from the main view. Then, our network regresses the 3D position of each joint by summing and averaging the coordinates of attention points on each surface after being weighted. To verify our method, we first tested ACRNet on the open-source ITOP dataset; meanwhile, we collected a new multi-view upper body movement dataset (UBM) on the trunk support trainer (TruST) to validate the capability of our model in real rehabilitation scenarios. Experimental results demonstrate the superiority of ACRNet compared with other state-of-the-art methods. We also validate the efficacy of each module in ACRNet. Furthermore, Our work analyzes the performance of ACRNet under the medical monitoring indicator. Because of the high accuracy and running speed, our model is suitable for real-time telemedicine settings. The source code is available at https://github.com/BoceHu/ACRNet
Transformers flexibly operate over sets of real-valued vectors representing task-specific entities and their attributes, where each vector might encode one word-piece token and its position in a sequence, or some piece of information that carries no position at all. But as set processors, transformers are at a disadvantage in reasoning over more general graph-structured data where nodes represent entities and edges represent relations between entities. To address this shortcoming, we generalize transformer attention to consider and update edge vectors in each transformer layer. We evaluate this relational transformer on a diverse array of graph-structured tasks, including the large and challenging CLRS Algorithmic Reasoning Benchmark. There, it dramatically outperforms state-of-the-art graph neural networks expressly designed to reason over graph-structured data. Our analysis demonstrates that these gains are attributable to relational attention's inherent ability to leverage the greater expressivity of graphs over sets.
In this work, we revisit the Transformer-based pre-trained language models and identify two different types of information confusion in position encoding and model representations, respectively. Firstly, we show that in the relative position encoding, the joint modeling about relative distances and directions brings confusion between two heterogeneous information. It may make the model unable to capture the associative semantics of the same distance and the opposite directions, which in turn affects the performance of downstream tasks. Secondly, we notice the BERT with Mask Language Modeling (MLM) pre-training objective outputs similar token representations (last hidden states of different tokens) and head representations (attention weights of different heads), which may make the diversity of information expressed by different tokens and heads limited. Motivated by the above investigation, we propose two novel techniques to improve pre-trained language models: Decoupled Directional Relative Position (DDRP) encoding and MTH pre-training objective. DDRP decouples the relative distance features and the directional features in classical relative position encoding. MTH applies two novel auxiliary regularizers besides MLM to enlarge the dissimilarities between (a) last hidden states of different tokens, and (b) attention weights of different heads. These designs allow the model to capture different categories of information more clearly, as a way to alleviate information confusion in representation learning for better optimization. Extensive experiments and ablation studies on GLUE benchmark demonstrate the effectiveness of our proposed methods.
Transformer models have made tremendous progress in various fields in recent years. In the field of computer vision, vision transformers (ViTs) also become strong alternatives to convolutional neural networks (ConvNets), yet they have not been able to replace ConvNets since both have their own merits. For instance, ViTs are good at extracting global features with attention mechanisms while ConvNets are more efficient in modeling local relationships due to their strong inductive bias. A natural idea that arises is to combine the strengths of both ConvNets and ViTs to design new structures. In this paper, we propose a new basic neural network operator named position-aware circular convolution (ParC) and its accelerated version Fast-ParC. The ParC operator can capture global features by using a global kernel and circular convolution while keeping location sensitiveness by employing position embeddings. Our Fast-ParC further reduces the O(n2) time complexity of ParC to O(n log n) using Fast Fourier Transform. This acceleration makes it possible to use global convolution in the early stages of models with large feature maps, yet still maintains the overall computational cost comparable with using 3x3 or 7x7 kernels. The proposed operation can be used in a plug-and-play manner to 1) convert ViTs to pure-ConvNet architecture to enjoy wider hardware support and achieve higher inference speed; 2) replacing traditional convolutions in the deep stage of ConvNets to improve accuracy by enlarging the effective receptive field. Experiment results show that our ParC op can effectively enlarge the receptive field of traditional ConvNets, and adopting the proposed op benefits both ViTs and ConvNet models on all three popular vision tasks, image classification, object
There are still two problems in SDD causing some inaccurate results: (1) In the process of feature extraction, with the layer-by-layer acquisition of semantic information, local information is gradually lost, resulting into less representative feature maps; (2) During the Non-Maximum Suppression (NMS) algorithm due to inconsistency in classification and regression tasks, the classification confidence and predicted detection position cannot accurately indicate the position of the prediction boxes. Methods: In order to address these aforementioned issues, we propose a new architecture, a modified version of Single Shot Multibox Detector (SSD), named Precise Single Stage Detector (PSSD). Firstly, we improve the features by adding extra layers to SSD. Secondly, we construct a simple and effective feature enhancement module to expand the receptive field step by step for each layer and enhance its local and semantic information. Finally, we design a more efficient loss function to predict the IOU between the prediction boxes and ground truth boxes, and the threshold IOU guides classification training and attenuates the scores, which are used by the NMS algorithm. Main Results: Benefiting from the above optimization, the proposed model PSSD achieves exciting performance in real-time. Specifically, with the hardware of Titan Xp and the input size of 320 pix, PSSD achieves 33.8 mAP at 45 FPS speed on MS COCO benchmark and 81.28 mAP at 66 FPS speed on Pascal VOC 2007 outperforming state-of-the-art object detection models. Besides, the proposed model performs significantly well with larger input size. Under 512 pix, PSSD can obtain 37.2 mAP with 27 FPS on MS COCO and 82.82 mAP with 40 FPS on Pascal VOC 2007. The experiment results prove that the proposed model has a better trade-off between speed and accuracy.
The use of autonomous vehicles for target localization in modern applications has emphasized their superior efficiency, improved safety, and cost advantages over human-operated methods. For localization tasks, autonomous vehicles can be used to increase efficiency and ensure that the target is localized as quickly and precisely as possible. However, devising a motion planning scheme to achieve these objectives in a computationally efficient manner suitable for real-time implementation is not straightforward. In this paper, we introduce a motion planning solution for enhanced target localization, leveraging Bernstein polynomial basis functions to approximate the probability distribution of the target's trajectory. This allows us to derive estimation performance criteria which are used by the motion planner to enhance the estimator efficacy. To conclude, we present simulation results that validate the effectiveness of the suggested algorithm.
Price movement prediction has always been one of the traders' concerns in financial market trading. In order to increase their profit, they can analyze the historical data and predict the price movement. The large size of the data and complex relations between them lead us to use algorithmic trading and artificial intelligence. This paper aims to offer an approach using Twin-Delayed DDPG (TD3) and the daily close price in order to achieve a trading strategy in the stock and cryptocurrency markets. Unlike previous studies using a discrete action space reinforcement learning algorithm, the TD3 is continuous, offering both position and the number of trading shares. Both the stock (Amazon) and cryptocurrency (Bitcoin) markets are addressed in this research to evaluate the performance of the proposed algorithm. The achieved strategy using the TD3 is compared with some algorithms using technical analysis, reinforcement learning, stochastic, and deterministic strategies through two standard metrics, Return and Sharpe ratio. The results indicate that employing both position and the number of trading shares can improve the performance of a trading system based on the mentioned metrics.
The purpose of navigation is to determine the position, velocity, and orientation of manned and autonomous platforms, humans, and animals. Obtaining accurate navigation commonly requires fusion between several sensors, such as inertial sensors and global navigation satellite systems, in a model-based, nonlinear estimation framework. Recently, data-driven approaches applied in various fields show state-of-the-art performance, compared to model-based methods. In this paper we review multidisciplinary, data-driven based navigation algorithms developed and experimentally proven at the Autonomous Navigation and Sensor Fusion Lab (ANSFL) including algorithms suitable for human and animal applications, varied autonomous platforms, and multi-purpose navigation and fusion approaches
In this paper, we present Position-to-Structure Attention Transformers (PS-Former), a Transformer-based algorithm for 3D point cloud recognition. PS-Former deals with the challenge in 3D point cloud representation where points are not positioned in a fixed grid structure and have limited feature description (only 3D coordinates ($x, y, z$) for scattered points). Existing Transformer-based architectures in this domain often require a pre-specified feature engineering step to extract point features. Here, we introduce two new aspects in PS-Former: 1) a learnable condensation layer that performs point downsampling and feature extraction; and 2) a Position-to-Structure Attention mechanism that recursively enriches the structural information with the position attention branch. Compared with the competing methods, while being generic with less heuristics feature designs, PS-Former demonstrates competitive experimental results on three 3D point cloud tasks including classification, part segmentation, and scene segmentation.
Monocular visual odometry consists of the estimation of the position of an agent through images of a single camera, and it is applied in autonomous vehicles, medical robots, and augmented reality. However, monocular systems suffer from the scale ambiguity problem due to the lack of depth information in 2D frames. This paper contributes by showing an application of the dense prediction transformer model for scale estimation in monocular visual odometry systems. Experimental results show that the scale drift problem of monocular systems can be reduced through the accurate estimation of the depth map by this model, achieving competitive state-of-the-art performance on a visual odometry benchmark.
We tackle the problem of sequential brick assembly with LEGO bricks to create combinatorial 3D structures. This problem is challenging since this brick assembly task encompasses the characteristics of combinatorial optimization problems. In particular, the number of assemblable structures increases exponentially as the number of bricks used increases. To solve this problem, we propose a new method to predict the scores of the next brick position by employing a U-shaped sparse 3D convolutional neural network. Along with the 3D convolutional network, a one-initialized brick-sized convolution filter is used to efficiently validate assembly constraints between bricks without training itself. By the nature of this one-initialized convolution filter, we can readily consider several different brick types by benefiting from modern implementation of convolution operations. To generate a novel structure, we devise a sampling strategy to determine the next brick position considering the satisfaction of assembly constraints. Moreover, our method is designed for either budget-free or budget-aware scenario where a budget may confine the number of bricks and their types. We demonstrate that our method successfully generates a variety of brick structures and outperforms existing methods with Bayesian optimization, deep graph generative model, and reinforcement learning.
Thousands of vulnerabilities are reported on a monthly basis to security repositories, such as the National Vulnerability Database. Among these vulnerabilities, software misconfiguration is one of the top 10 security risks for web applications. With this large influx of vulnerability reports, software fingerprinting has become a highly desired capability to discover distinctive and efficient signatures and recognize reportedly vulnerable software implementations. Due to the exponential worst-case complexity of fingerprint matching, designing more efficient methods for fingerprinting becomes highly desirable, especially for variability-intensive systems where optional features add another exponential factor to its analysis. This position paper presents our vision of a framework that lifts model learning and family-based analysis principles to software fingerprinting. In this framework, we propose unifying databases of signatures into a featured finite state machine and using presence conditions to specify whether and in which circumstances a given input-output trace is observed. We believe feature-based signatures can aid performance improvements by reducing the size of fingerprints under analysis.
The basic idea of RSS-based indoor positioning is to estimate the receiver location by matching the measured received signal strength indicator (RSSI) with preestablished RSSI collections with corresponding locations, known as the radio map. Hence, constructing an accurate radio map directly relates to accurate positioning performance in RSS-based indoor positioning. RSS-based indoor positioning can be easily conducted with a radio map that surveys every location, but a complete radio map cannot be constructed when the map area includes locations that are physically impossible to reach or denied access. In addition, measurement errors or device problems can occur during the survey, resulting in degradation of the radio map. We analyzed incidents that occurred in actual RSSI surveys that could disrupt the construction of the radio map and proposed methods to construct a more accurate radio map.
Many emerging technologies for the next generation wireless network prefer line-of-sight (LOS) propagation conditions to fully release their performance advantages. This paper studies 3D unmanned aerial vehicle (UAV) placement to establish LOS links for two ground terminals in deep shadow in a dense urban environment. The challenge is that the LOS region for the feasible UAV positions can be arbitrary due to the complicated structure of the environment. While most existing works rely on simplified stochastic LOS models and problem relaxations, this paper focuses on establishing theoretical guarantees for the optimal UAV placement to ensure LOS conditions for two ground users in an actual propagation environment. It is found that it suffices to search a bounded 2D area for the globally optimal 3D UAV position. Thus, this paper develops an exploration-exploitation algorithm with a linear trajectory length and achieves above 99% global optimality over several real city environments being tested in our experiments. To further enhance the search capability in an ultra-dense environment, a dynamic multi-stage algorithm is developed and theoretically shown to find an $\epsilon$-optimal UAV position with a search length $O(1/\epsilon)$. Significant performance advantages are demonstrated in several numerical experiments for wireless communication relaying and wireless power transfer.
This paper proposes a novel framework for real-time localization and egomotion tracking of a vehicle in a reference map. The core idea is to map the semantic objects observed by the vehicle and register them to their corresponding objects in the reference map. While several recent works have leveraged semantic information for cross-view localization, the main contribution of this work is a view-invariant formulation that makes the approach directly applicable to any viewpoint configuration for which objects are detectable. Another distinctive feature is robustness to changes in the environment/objects due to a data association scheme suited for extreme outlier regimes (e.g., 90% association outliers). To demonstrate our framework, we consider an example of localizing a ground vehicle in a reference object map using only cars as objects. While only a stereo camera is used for the ground vehicle, we consider reference maps constructed a priori from ground viewpoints using stereo cameras and Lidar scans, and georeferenced aerial images captured at a different date to demonstrate the framework's robustness to different modalities, viewpoints, and environment changes. Evaluations on the KITTI dataset show that over a 3.7 km trajectory, localization occurs in 36 sec and is followed by real-time egomotion tracking with an average position error of 8.5 m in a Lidar reference map, and on an aerial object map where 77% of objects are outliers, localization is achieved in 71 sec with an average position error of 7.9 m.
Adversarial patch-based attacks aim to fool a neural network with an intentionally generated noise, which is concentrated in a particular region of an input image. In this work, we perform an in-depth analysis of different patch generation parameters, including initialization, patch size, and especially positioning a patch in an image during training. We focus on the object vanishing attack and run experiments with YOLOv3 as a model under attack in a white-box setting and use images from the COCO dataset. Our experiments have shown, that inserting a patch inside a window of increasing size during training leads to a significant increase in attack strength compared to a fixed position. The best results were obtained when a patch was positioned randomly during training, while patch position additionally varied within a batch.