Ghost imaging radar is a new system of gaze imaging radar with high detection sensitivity, super-resolution and better anti-interference performance, but the relative motion between the radar system and the target will make the target imaging deteriorate. This paper proposes to perform absolute position localisation of a single target in the field of view by weighting the correlation strength of a single frame image of rough target, and to compensate translation of the reference arm speckle according to the localisation and tracking trajectory to accumulate the rough image into a high quality image. The proposed correlation intensity weighted localization and tracking imaging method has been verified by simulation to be able to locate and image targets in the field of view well.
Pairwise debiasing is one of the most effective strategies in reducing position bias in learning-to-rank (LTR) models. However, limiting the scope of this strategy, are the underlying assumptions required by many pairwise debiasing approaches. In this paper, we develop an approach based on a minimalistic set of assumptions that can be applied to a much broader range of user browsing patterns and arbitrary presentation layouts. We implement the approach as a simplified version of the Unbiased LambdaMART and demonstrate that it retains the underlying unbiasedness property in a wider variety of settings than the original algorithm. Finally, using simulations with "golden" relevance labels, we will show that the simplified version compares favourably with the original Unbiased LambdaMART when the examination of different positions in a ranked list is not assumed to be independent.
Surface defect detection is an extremely crucial step to ensure the quality of industrial products. Nowadays, convolutional neural networks (CNNs) based on encoder-decoder architecture have achieved tremendous success in various defect detection tasks. However, due to the intrinsic locality of convolution, they commonly exhibit a limitation in explicitly modeling long-range interactions, critical for pixel-wise defect detection in complex cases, e.g., cluttered background and illegible pseudo-defects. Recent transformers are especially skilled at learning global image dependencies but with limited local structural information necessary for detailed defect location. To overcome the above limitations, we propose an efficient hybrid transformer architecture, termed Defect Transformer (DefT), for surface defect detection, which incorporates CNN and transformer into a unified model to capture local and non-local relationships collaboratively. Specifically, in the encoder module, a convolutional stem block is firstly adopted to retain more detailed spatial information. Then, the patch aggregation blocks are used to generate multi-scale representation with four hierarchies, each of them is followed by a series of DefT blocks, which respectively include a locally position-aware block for local position encoding, a lightweight multi-pooling self-attention to model multi-scale global contextual relationships with good computational efficiency, and a convolutional feed-forward network for feature transformation and further location information learning. Finally, a simple but effective decoder module is proposed to gradually recover spatial details from the skip connections in the encoder. Extensive experiments on three datasets demonstrate the superiority and efficiency of our method compared with other CNN- and transformer-based networks.
Transformers have gained increasing popularity in a wide range of applications, including Natural Language Processing (NLP), Computer Vision and Speech Recognition, because of their powerful representational capacity. However, harnessing this representational capacity effectively requires a large amount of data, strong regularization, or both, to mitigate overfitting. Recently, the power of the Transformer has been unlocked by self-supervised pretraining strategies based on masked autoencoders which rely on reconstructing masked inputs, directly, or contrastively from unmasked content. This pretraining strategy which has been used in BERT models in NLP, Wav2Vec models in Speech and, recently, in MAE models in Vision, forces the model to learn about relationships between the content in different parts of the input using autoencoding related objectives. In this paper, we propose a novel, but surprisingly simple alternative to content reconstruction~-- that of predicting locations from content, without providing positional information for it. Doing so requires the Transformer to understand the positional relationships between different parts of the input, from their content alone. This amounts to an efficient implementation where the pretext task is a classification problem among all possible positions for each input token. We experiment on both Vision and Speech benchmarks, where our approach brings improvements over strong supervised training baselines and is comparable to modern unsupervised/self-supervised pretraining methods. Our method also enables Transformers trained without position embeddings to outperform ones trained with full position information.
Nowadays, it is a trend that using a parallel-decoupled encoderdecoder (PDED) framework in scene text recognition for its flexibility and efficiency. However, due to the inconsistent information content between queries and keys in the parallel positional attention module (PPAM) used in this kind of framework(queries: position information, keys: context and position information), visual misalignment tends to appear when confronting hard samples(e.g., blurred texts, irregular texts, or low-quality images). To tackle this issue, in this paper, we propose a dual parallel attention network (DPAN), in which a newly designed parallel context attention module (PCAM) is cascaded with the original PPAM, using linguistic contextual information to compensate for the information inconsistency between queries and keys. Specifically, in PCAM, we take the visual features from PPAM as inputs and present a bidirectional language model to enhance them with linguistic contexts to produce queries. In this way, we make the information content of the queries and keys consistent in PCAM, which helps to generate more precise visual glimpses to improve the entire PDED framework’s accuracy and robustness. Experimental results verify the effectiveness of the proposed PCAM, showing the necessity of keeping the information consistency between queries and keys in the attention mechanism. On six benchmarks, including regular text and irregular text, the performance of DPAN surpasses the existing leading methods by large margins, achieving new state-of-the-art performance. The code is available on https://github.com/Jackandrome/DPAN.
We leverage pre-trained language models to solve the task of complex NER for two low-resource languages: Chinese and Spanish. We use the technique of Whole Word Masking(WWM) to boost the performance of masked language modeling objective on large and unsupervised corpora. We experiment with multiple neural network architectures, incorporating CRF, BiLSTMs, and Linear Classifiers on top of a fine-tuned BERT layer. All our models outperform the baseline by a significant margin and our best performing model obtains a competitive position on the evaluation leaderboard for the blind test set.
Indoor Positioning based on Machine Learning has drawn increasing attention both in the academy and the industry as meaningful information from the reference data can be extracted. Many researchers are using supervised, semi-supervised, and unsupervised Machine Learning models to reduce the positioning error and offer reliable solutions to the end-users. In this article, we propose a new architecture by combining Convolutional Neural Network (CNN), Long short-term memory (LSTM) and Generative Adversarial Network (GAN) in order to increase the training data and thus improve the position accuracy. The proposed combination of supervised and unsupervised models was tested in 17 public datasets, providing an extensive analysis of its performance. As a result, the positioning error has been reduced in more than 70% of them.
During the radiotherapy treatment of patients with lung cancer, the radiation delivered to healthy tissue around the tumor needs to be minimized, which is difficult because of respiratory motion and the latency of linear accelerator systems. In the proposed study, we first use the Lucas-Kanade pyramidal optical flow algorithm to perform deformable image registration of chest computed tomography scan images of four patients with lung cancer. We then track three internal points close to the lung tumor based on the previously computed deformation field and predict their position with a recurrent neural network (RNN) trained using real-time recurrent learning (RTRL) and gradient clipping. The breathing data is quite regular, sampled at approximately 2.5Hz, and includes artificial drift in the spine direction. The amplitude of the motion of the tracked points ranged from 12.0mm to 22.7mm. Finally, we propose a simple method for recovering and predicting 3D tumor images from the tracked points and the initial tumor image based on a linear correspondence model and Nadaraya-Watson non-linear regression. The root-mean-square error, maximum error, and jitter corresponding to the RNN prediction on the test set were smaller than the same performance measures obtained with linear prediction and least mean squares (LMS). In particular, the maximum prediction error associated with the RNN, equal to 1.51mm, is respectively 16.1% and 5.0% lower than the maximum error associated with linear prediction and LMS. The average prediction time per time step with RTRL is equal to 119ms, which is less than the 400ms marker position sampling time. The tumor position in the predicted images appears visually correct, which is confirmed by the high mean cross-correlation between the original and predicted images, equal to 0.955.
G-Protein Coupled Receptors (GPCRs) are a big family of eukaryotic cell transmembrane proteins, responsible for numerous biological processes. From a practical viewpoint around 34\% of the drugs approved by the US Food and Drug Administration target these receptors. They can be analyzed from their simulated molecular dynamics, including the prediction of their behavior in the presence of drugs. In this paper, the capability of Long Short-Term Memory Networks (LSTMs) are evaluated to learn and predict the molecular dynamic trajectories of a receptor. Several models were trained with the 3D position of the amino acids of the receptor considering different transformations on the position of the amino acid, such as their centers of mass, the geometric centers and the position of the $\alpha$--carbon for each amino acid. The error of the prediction of the position was evaluated by the mean average error (MAE) and root-mean-square deviation (RMSD). The LSTM models show a robust performance, with results comparable to the state-of-the-art in non-dynamic 3D predictions. The best MAE and RMSD values were found for the mass center of the amino acids with 0.078 {\AA} and 0.156 {\AA} respectively. This work shows the potential of LSTM to predict the molecular dynamics of GPRCs.
Absolute pose regressor (APR) networks are trained to estimate the pose of the camera given a captured image. They compute latent image representations from which the camera position and orientation are regressed. APRs provide a different tradeoff between localization accuracy, runtime, and memory, compared to structure-based localization schemes that provide state-of-the-art accuracy. In this work, we introduce Camera Pose Auto-Encoders (PAEs), multilayer perceptrons that are trained via a Teacher-Student approach to encode camera poses using APRs as their teachers. We show that the resulting latent pose representations can closely reproduce APR performance and demonstrate their effectiveness for related tasks. Specifically, we propose a light-weight test-time optimization in which the closest train poses are encoded and used to refine camera position estimation. This procedure achieves a new state-of-the-art position accuracy for APRs, on both the CambridgeLandmarks and 7Scenes benchmarks. We also show that train images can be reconstructed from the learned pose encoding, paving the way for integrating visual information from the train set at a low memory cost. Our code and pre-trained models are available at https://github.com/yolish/camera-pose-auto-encoders.
Online learning to rank (OLTR) interactively learns to choose lists of items from a large collection based on certain click models that describe users' click behaviors. Most recent works for this problem focus on the stochastic environment where the item attractiveness is assumed to be invariant during the learning process. In many real-world scenarios, however, the environment could be dynamic or even arbitrarily changing. This work studies the OLTR problem in both stochastic and adversarial environments under the position-based model (PBM). We propose a method based on the follow-the-regularized-leader (FTRL) framework with Tsallis entropy and develop a new self-bounding constraint especially designed for PBM. We prove the proposed algorithm simultaneously achieves $O(\log{T})$ regret in the stochastic environment and $O(m\sqrt{nT})$ regret in the adversarial environment, where $T$ is the number of rounds, $n$ is the number of items and $m$ is the number of positions. We also provide a lower bound of order $\Omega(m\sqrt{nT})$ for adversarial PBM, which matches our upper bound and improves over the state-of-the-art lower bound. The experiments show that our algorithm could simultaneously learn in both stochastic and adversarial environments and is competitive compared to existing methods that are designed for a single environment.
In recent years, an increasing amount of work has focused on differentiable physics simulation and has produced a set of open source projects such as Tiny Differentiable Simulator, Nimble Physics, diffTaichi, Brax, Warp, Dojo and DiffCoSim. By making physics simulations end-to-end differentiable, we can perform gradient-based optimization and learning tasks. A majority of differentiable simulators consider collisions and contacts between objects, but they use different contact models for differentiability. In this paper, we overview four kinds of differentiable contact formulations - linear complementarity problems (LCP), convex optimization models, compliant models and position-based dynamics (PBD). We analyze and compare the gradients calculated by these models and show that the gradients are not always correct. We also demonstrate their ability to learn an optimal control strategy by comparing the learned strategies with the optimal strategy in an analytical form. The codebase to reproduce the experiment results is available at https://github.com/DesmondZhong/diff_sim_grads.
Due to their shorter operating range and large bandwidth, automotive radars can resolve many reflections from their targets of interest, mainly vehicles. This calls for the use of extended-target models in place of simpler and more widely-adopted point-like target models. However, despite some preliminary work, the fundamental connection between the radar's accuracy as a function of the target vehicle state (range, orientation, shape) and radar properties remains largely unknown for extended targets. In this work, we first devise a mathematically tractable analytical model for a vehicle with arbitrary shape, modeled as an extended target parameterized by the center position, the orientation (heading) and the perimeter contour. We show that the derived expressions of the backscatter signal are tractable and correctly capture the effects of the extended-vehicle shape. Analytical derivations of the exact and approximate hybrid Cram\'er-Rao bounds for the position, orientation and contour are provided, which reveal connections with the case of point-like target and uncover the main dependencies with the received energy, bandwidth, and array size. The theoretical investigation is performed on the two different cases of known and unknown vehicle shape. Insightful simulation results are finally presented to validate the theoretical findings, including an analysis of the diversity effect of multiple radars sensing the extended target.
Mission planners for aircraft operating under threat of detection by ground-based radar systems are concerned with the probability of detection. Current path planning methods for such scenarios consider the aircraft pose, radar position, and radar parameters to be deterministic and known. This paper presents a framework for incorporating uncertainty in these quantities into a radar detection model that is used by a path planner. The developed path planner evaluates the radar detection risk in the presence of uncertainties and uses linear covariance analysis to efficiently generate error budgets. The error budgets identify the contribution of each source of uncertainty (e.g., sensor measurement noise, radar position uncertainty) to the overall variability in the probability of detection. The framework is applied to a modified visibility graph path planner that uses the detection risk and its variability to calculate path adjustments, which maintain the detection risk below a specified threshold. The results show that the framework is effective at providing actionable information to the mission planner that improves the final planned path and reduces the detection risk.
In robotics, Visual Place Recognition is a continuous process that receives as input a video stream to produce a hypothesis of the robot's current position within a map of known places. This task requires robust, scalable, and efficient techniques for real applications. This work proposes a detailed taxonomy of techniques using sequential descriptors, highlighting different mechanism to fuse the information from the individual images. This categorization is supported by a complete benchmark of experimental results that provides evidence on the strengths and weaknesses of these different architectural choices. In comparison to existing sequential descriptors methods, we further investigate the viability of Transformers instead of CNN backbones, and we propose a new ad-hoc sequence-level aggregator called SeqVLAD, which outperforms prior state of the art on different datasets. The code is available at https://github.com/vandal-vpr/vg-transformers.
Even though term-based methods such as BM25 provide strong baselines in ranking, under certain conditions they are dominated by large pre-trained masked language models (MLMs) such as BERT. To date, the source of their effectiveness remains unclear. Is it their ability to truly understand the meaning through modeling syntactic aspects? We answer this by manipulating the input order and position information in a way that destroys the natural sequence order of query and passage and shows that the model still achieves comparable performance. Overall, our results highlight that syntactic aspects do not play a critical role in the effectiveness of re-ranking with BERT. We point to other mechanisms such as query-passage cross-attention and richer embeddings that capture word meanings based on aggregated context regardless of the word order for being the main attributions for its superior performance.
Due to the extreme complexity of scale and shape as well as the uncertainty of the predicted location, salient object detection in optical remote sensing images (RSI-SOD) is a very difficult task. The existing SOD methods can satisfy the detection performance for natural scene images, but they are not well adapted to RSI-SOD due to the above-mentioned image characteristics in remote sensing images. In this paper, we propose a novel Attention Guided Network (AGNet) for SOD in optical RSIs, including position enhancement stage and detail refinement stage. Specifically, the position enhancement stage consists of a semantic attention module and a contextual attention module to accurately describe the approximate location of salient objects. The detail refinement stage uses the proposed self-refinement module to progressively refine the predicted results under the guidance of attention and reverse attention. In addition, the hybrid loss is applied to supervise the training of the network, which can improve the performance of the model from three perspectives of pixel, region and statistics. Extensive experiments on two popular benchmarks demonstrate that AGNet achieves competitive performance compared to other state-of-the-art methods. The code will be available at https://github.com/NuaaYH/AGNet.
We dramatically improve convergence speed and global exploration capabilities of particle swarm optimization (PSO) through a targeted position-mutated elitism (PSO-TPME). The three key innovations address particle classification, elitism, and mutation in the cognitive and social model. PSO-TPME is benchmarked against five popular PSO variants for multi-dimensional functions, which are extensively adopted in the optimization field, In particular, the convergence accuracy, convergence speed, and the capability to find global minima is investigated. The statistical error is assessed by numerous repetitions. The simulations demonstrate that proposed PSO variant outperforms the other variants in terms of convergence rate and accuracy by orders of magnitude.
Reinforcement Learning (RL) algorithms show amazing performance in recent years, but placing RL in real-world applications such as self-driven vehicles may suffer safety problems. A self-driven vehicle moving to a target position following a learned policy may suffer a vehicle with unpredictable aggressive behaviors or even being pursued by a vehicle following a Nash strategy. To address the safety issue of the self-driven vehicle in this scenario, this paper conducts a preliminary study based on a system of robots. A safe RL framework with safety guarantees is developed for a robot being pursued but with objectives covering more than capture-avoidance. Simulations and experiments are conducted based on the system of robots to evaluate the effectiveness of the developed safe RL framework.
When a government makes many different policy decisions, lobbying can be viewed as a contest between the government and many different special interest groups. The government fights lobbying by interest groups with its own political capital. In this world, we find that a government wants to `sell protection' -- give favourable treatment in exchange for contributions -- to certain interest groups. It does this in order to build its own `war chest' of political capital, which improves its position in fights with other interest groups. And it does so until it wins all remaining contests with certainty. This stands in contrast to existing models that often view lobbying as driven by information or agency problems.