The human-centric explainable artificial intelligence (HCXAI) community has raised the need for framing the explanation process as a conversation between human and machine. In this position paper, we establish desiderata for Mediators, text-based conversational agents which are capable of explaining the behavior of neural models interactively using natural language. From the perspective of natural language processing (NLP) research, we engineer a blueprint of such a Mediator for the task of sentiment analysis and assess how far along current research is on the path towards dialogue-based explanations.
Safety is the foremost concern for autonomous platooning. The vehicle-to-vehicle (V2V) communication delay and the sudden appearance of obstacles will trigger the safety of the intended functionality (SOTIF) issues for autonomous platooning. This research proposes a holistic robust motion controller framework (MCF) for an intelligent and connected vehicle platoon system. The MCF utilizes a hierarchical structure to resolve the longitudinal string stability and the lateral control problem under the complex driving environment and time-varying communication delay. Firstly, the H-infinity feedback controller is developed to ensure the robustness of the platoon under time-varying communication delay in the upper-level coordination layer (UCL). The output from UCL will be delivered to the lower-level motion-planning layer (LML) as reference signals. Secondly, the model predictive control (MPC) algorithm is implemented in the LML to achieve multi-objective control, which comprehensively considers the reference signals, the artificial potential field, and multiple vehicle dynamics constraints. Furthermore, three critical scenarios are co-simulated for case studies, including platooning under time-varying communication delay, merging, and obstacle avoidance scenarios. The simulation results indicate that, compared with single-structure MPC, the proposed MCF can offer a better suppression on position error propagation, and get improvements on maximum position error in the three scenarios by $19.2\%$, $59.8\%$, and $15.3\%$, respectively. Last, the practicability and effectiveness of the proposed MCF are verified via hardware-in-the-loop experiment. The average conducting time of the proposed method on Speedgoat real-time target machine is 1.1 milliseconds, which meets the real-time requirements.
The task of inserting text into a specified position in a passage, known as fill in the blank (FitB), is useful for a variety of applications where writers interact with a natural language generation (NLG) system to craft text. While previous work has tackled this problem with models trained specifically to do the fill-in-the-blank task, a more useful model is one that can effectively perform _both_ FitB and continuation. In this work, we evaluate the feasibility of using a single model to do both tasks. We show that models pre-trained with a FitB-style objective are capable of both tasks, while models pre-trained for continuation are not. Finally, we show how FitB models can be easily finetuned to allow for fine-grained control over the length and word choice of the generation.
Positional encoding is important for vision transformer (ViT) to capture the spatial structure of the input image. General effectiveness has been proven in ViT. In our work we propose to train ViT to recognize the positional label of patches of the input image, this apparently simple task actually yields a meaningful self-supervisory task. Based on previous work on ViT positional encoding, we propose two positional labels dedicated to 2D images including absolute position and relative position. Our positional labels can be easily plugged into various current ViT variants. It can work in two ways: (a) As an auxiliary training target for vanilla ViT (e.g., ViT-B and Swin-B) for better performance. (b) Combine the self-supervised ViT (e.g., MAE) to provide a more powerful self-supervised signal for semantic feature learning. Experiments demonstrate that with the proposed self-supervised methods, ViT-B and Swin-B gain improvements of 1.20% (top-1 Acc) and 0.74% (top-1 Acc) on ImageNet, respectively, and 6.15% and 1.14% improvement on Mini-ImageNet.
Previous work generally believes that improving the spatial invariance of convolutional networks is the key to object counting. However, after verifying several mainstream counting networks, we surprisingly found too strict pixel-level spatial invariance would cause overfit noise in the density map generation. In this paper, we try to use locally connected Gaussian kernels to replace the original convolution filter to estimate the spatial position in the density map. The purpose of this is to allow the feature extraction process to potentially stimulate the density map generation process to overcome the annotation noise. Inspired by previous work, we propose a low-rank approximation accompanied with translation invariance to favorably implement the approximation of massive Gaussian convolution. Our work points a new direction for follow-up research, which should investigate how to properly relax the overly strict pixel-level spatial invariance for object counting. We evaluate our methods on 4 mainstream object counting networks (i.e., MCNN, CSRNet, SANet, and ResNet-50). Extensive experiments were conducted on 7 popular benchmarks for 3 applications (i.e., crowd, vehicle, and plant counting). Experimental results show that our methods significantly outperform other state-of-the-art methods and achieve promising learning of the spatial position of objects.
Signals of opportunity (SOPs) are a promising technique that can be used for relative positioning in areas where global navigation satellite system (GNSS) information is unreliable or unavailable. This technique processes features of the various signals transmitted over a broad wireless spectrum to enable a receiver to position itself in space. This work examines the frequency selection problem in order to achieve fast and accurate positioning using only the received signal strength (RSS) of the surrounding signals. Starting with a prior belief, the problem of searching for a frequency band that best matches a predicted location trajectory is investigated. To maximize the accuracy of the position estimate, a ranking-and-selection problem is mathematically formulated. A knowledge-gradient (KG) algorithm from optimal learning theory is proposed that uses correlations in the Bayesian prior beliefs of the frequency band values to dramatically reduce the algorithm's processing time. The technique is experimentally tested for a practical scenario of an unmanned aerial vehicle (UAV) moving around a GPS-denied environment, with obtained results demonstrating its validity and practical applicability.
Extracting Handwritten text is one of the most important components of digitizing information and making it available for large scale setting. Handwriting Optical Character Reader (OCR) is a research problem in computer vision and natural language processing computing, and a lot of work has been done for English, but unfortunately, very little work has been done for low resourced languages such as Urdu. Urdu language script is very difficult because of its cursive nature and change of shape of characters based on it's relative position, therefore, a need arises to propose a model which can understand complex features and generalize it for every kind of handwriting style. In this work, we propose a transformer based Urdu Handwritten text extraction model. As transformers have been very successful in Natural Language Understanding task, we explore them further to understand complex Urdu Handwriting.
The definition and representation of planning problems is at the heart of AI planning research. A key part is the representation of action models. Decades of advances improving declarative action model representations resulted in numerous theoretical advances, and capable, working, domain-independent planners. However, despite the maturity of the field, AI planning technology is still rarely used outside the research community, suggesting that current representations fail to capture real-world requirements, such as utilizing complex mathematical functions and models learned from data. We argue that this is because the modeling process is assumed to have taken place and completed prior to the planning process, i.e., offline modeling for offline planning. There are several challenges inherent to this approach, including: limited expressiveness of declarative modeling languages; early commitment to modeling choices and computation, that preclude using the most appropriate resolution for each action model -- which can only be known during planning; and difficulty in reliably using non-declarative, learned, models. We therefore suggest to change the AI planning process, such that is carries out online modeling in offline planning, i.e., the use of action models that are computed or even generated as part of the planning process, as they are accessed. This generalizes the existing approach (offline modeling). The proposed definition admits novel planning processes, and we suggest one concrete implementation, demonstrating the approach. We sketch initial results that were obtained as part of a first attempt to follow this approach by planning with action cost estimators. We conclude by discussing open challenges.
Session-based recommendation aims to generate recommendations for the next item of users' interest based on a given session. In this manuscript, we develop prospective preference enhanced mixed attentive model (P2MAM) to generate session-based recommendations using two important factors: temporal patterns and estimates of users' prospective preferences. Unlike existing methods, P2MAM models the temporal patterns using a light-weight while effective position-sensitive attention mechanism. In P2MAM, we also leverage the estimate of users' prospective preferences to signify important items, and generate better recommendations. Our experimental results demonstrate that P2MAM models significantly outperform the state-of-the-art methods in six benchmark datasets, with an improvement as much as 19.2%. In addition, our run-time performance comparison demonstrates that during testing, P2MAM models are much more efficient than the best baseline method, with a significant average speedup of 47.7 folds.
This work addresses the problem of discovering non-linear interpretable paths in the latent space of pre-trained GANs in a model-agnostic manner. In the proposed method, the discovery is driven by a set of pairs of natural language sentences with contrasting semantics, named semantic dipoles, that serve as the limits of the interpretation that we require by the trainable latent paths to encode. By using the pre-trained CLIP encoder, the sentences are projected into the vision-language space, where they serve as dipoles, and where RBF-based warping functions define a set of non-linear directional paths, one for each semantic dipole, allowing in this way traversals from one semantic pole to the other. By defining an objective that discovers paths in the latent space of GANs that generate changes along the desired paths in the vision-language embedding space, we provide an intuitive way of controlling the underlying generative factors and address some of the limitations of the state-of-the-art works, namely, that a) they are typically tailored to specific GAN architectures (i.e., StyleGAN), b) they disregard the relative position of the manipulated and the original image in the image embedding and the relative position of the image and the text embeddings, and c) they lead to abrupt image manipulations and quickly arrive at regions of low density and, thus, low image quality, providing limited control of the generative factors. We provide extensive qualitative and quantitative results that demonstrate our claims with two pre-trained GANs, and make the code and the pre-trained models publicly available at: https://github.com/chi0tzp/ContraCLIP
We propose a method SPGNet for 3D human pose estimation that mixes multi-dimensional re-projection into supervised learning. In this method, the 2D-to-3D-lifting network predicts the global position and coordinates of the 3D human pose. Then, we re-project the estimated 3D pose back to the 2D key points along with spatial adjustments. The loss functions compare the estimated 3D pose with the 3D pose ground truth, and re-projected 2D pose with the input 2D pose. In addition, we propose a kinematic constraint to restrict the predicted target with constant human bone length. Based on the estimation results for the dataset Human3.6M, our approach outperforms many state-of-the-art methods both qualitatively and quantitatively.
This paper presents a new type of hybrid model for Bayesian optimization (BO) adept at managing mixed variables, encompassing both quantitative (continuous and integer) and qualitative (categorical) types. Our proposed new hybrid models (named hybridM) merge the Monte Carlo Tree Search structure (MCTS) for categorical variables with Gaussian Processes (GP) for continuous ones. hybridM leverages the upper confidence bound tree search (UCTS) for MCTS strategy, showcasing the tree architecture's integration into Bayesian optimization. Our innovations, including dynamic online kernel selection in the surrogate modeling phase and a unique UCTS search strategy, position our hybrid models as an advancement in mixed-variable surrogate models. Numerical experiments underscore the superiority of hybrid models, highlighting their potential in Bayesian optimization.
In this paper, we propose PETRv2, a unified framework for 3D perception from multi-view images. Based on PETR, PETRv2 explores the effectiveness of temporal modeling, which utilizes the temporal information of previous frames to boost 3D object detection. More specifically, we extend the 3D position embedding (3D PE) in PETR for temporal modeling. The 3D PE achieves the temporal alignment on object position of different frames. A feature-guided position encoder is further introduced to improve the data adaptability of 3D PE. To support for multi-task learning (e.g., BEV segmentation and 3D lane detection), PETRv2 provides a simple yet effective solution by introducing task-specific queries, which are initialized under different spaces. PETRv2 achieves state-of-the-art performance on 3D object detection, BEV segmentation and 3D lane detection. Detailed robustness analysis is also conducted on PETR framework. We hope PETRv2 can serve as a strong baseline for 3D perception. Code is available at \url{https://github.com/megvii-research/PETR}.
With the recent proliferation of artificial intelligence systems, there has been a surge in the demand for explainability of these systems. Explanations help to reduce system opacity, support transparency, and increase stakeholder trust. In this position paper, we discuss synergies between requirements engineering (RE) and Explainable AI (XAI). We highlight challenges in the field of XAI, and propose a framework and research directions on how RE practices can help to mitigate these challenges.
Recent studies show that paddings in convolutional neural networks encode absolute position information which can negatively affect the model performance for certain tasks. However, existing metrics for quantifying the strength of positional information remain unreliable and frequently lead to erroneous results. To address this issue, we propose novel metrics for measuring (and visualizing) the encoded positional information. We formally define the encoded information as PPP (Position-information Pattern from Padding) and conduct a series of experiments to study its properties as well as its formation. The proposed metrics measure the presence of positional information more reliably than the existing metrics based on PosENet and a test in F-Conv. We also demonstrate that for any extant (and proposed) padding schemes, PPP is primarily a learning artifact and is less dependent on the characteristics of the underlying padding schemes.
We propose a data-driven optimization-based pre-compensation method to improve the contour tracking performance of precision motion stages by modifying the reference trajectory and without modifying any built-in low-level controllers. The position of the precision motion stage is predicted with data-driven models, a linear low-fidelity model is used to optimize traversal time, by changing the path velocity and acceleration profiles then a non-linear high-fidelity model is used to refine the previously found time-optimal solution. We experimentally demonstrate that the proposed method is capable of simultaneously improving the productivity and accuracy of a high precision motion stage. Given the data-based nature of the models, the proposed method can easily be adapted to a wide family of precision motion systems.
This paper proposes exploiting the spatial correlation of wireless channel statistics beyond the conventional received signal strength maps by constructing statistical radio maps to predict any relevant channel statistics to assist communications. Specifically, from stored channel samples acquired by previous users in the network, we use Gaussian processes (GPs) to estimate quantiles of the channel distribution at a new position using a non-parametric model. This prior information is then used to select the transmission rate for some target level of reliability. The approach is tested with synthetic data, simulated from urban micro-cell environments, highlighting how the proposed solution helps to reduce the training estimation phase, which is especially attractive for the tight latency constraints inherent to ultra-reliable low-latency (URLLC) deployments.
Sequence diversity is one of the major challenges in the design of diagnostic, prophylactic and therapeutic interventions against viruses. DiMA is a novel tool that is big data-ready and designed to facilitate the dissection of sequence diversity dynamics for viruses. DiMA stands out from other diversity analysis tools by offering various unique features. DiMA provides a quantitative overview of sequence (nucleotide/protein) diversity by use of Shannon's entropy corrected for size bias, applied via a user-defined k-mer sliding window to an input alignment file, and each k-mer position is dissected to various diversity motifs. The motifs are defined based on the probability of distinct sequences at a given k-mer position, whereby an index is the predominant sequence, while all the others are (total) variants to the index. The total variants are sub-classified into the major (most common) variant, minor variants (occurring more than once and of frequency lower than the major), and the unique (singleton) variants. DiMA allows user-defined, sequence metadata enrichment for analyses of the motifs. The application of DiMA was demonstrated for the alignment data of the relatively conserved Spike protein (2,106,985 sequences) of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and the relatively highly diverse Pol protein (3,874) of human immunodeficiency virus-1 (HIV-1). The tool is publicly available as a web server (https://dima.bezmialem.edu.tr), as a Python library (via PyPi) and as a command line client (Via GitHub).
For the first time, this position paper introduces a fundamental link between tensor networks (TNs) and Green AI, highlighting their synergistic potential to enhance both the inclusivity and sustainability of AI research. We argue that TNs are valuable for Green AI due to their strong mathematical backbone and inherent logarithmic compression potential. We undertake a comprehensive review of the ongoing discussions on Green AI, emphasizing the importance of sustainability and inclusivity in AI research to demonstrate the significance of establishing the link between Green AI and TNs. To support our position, we first provide a comprehensive overview of efficiency metrics proposed in Green AI literature and then evaluate examples of TNs in the fields of kernel machines and deep learning using the proposed efficiency metrics. This position paper aims to incentivize meaningful, constructive discussions by bridging fundamental principles of Green AI and TNs. We advocate for researchers to seriously evaluate the integration of TNs into their research projects, and in alignment with the link established in this paper, we support prior calls encouraging researchers to treat Green AI principles as a research priority.
This paper presents general modal dual Quaternion (DQ) kinematics for multisection continuum arms. DQ's produce higher accuracy than homogeneous transformation matrices (HTM) when transformed to modal shape functions (MSF) of similar order and are numerically stable. Thus, the model is compact, more accurate and computationally efficient than the modal kinematics proposed by the author based on HTM's. Also, DQ kinematics does not suffer from singularity related limitations of Euler angle based inverse orientation kinematics. Recursive schemes for deriving DQ's and DQ Jacobians are also presented and can be extended arbitrarily. Both modal HTM and modal DQ kinematics are then applied to solve illustrative spatial inverse position and orientation tracking problems. Based on the results, this paper quantitatively compares both methods and highlights the advantages of modal DQ kinematics. The proposed DQ kinematics are easily extensible to variable length multisection continuum arm with general actuator configurations.