Search

We tackle the challenge of uncertainty quantification in the localization of a sound source within adverse acoustic environments. Estimating the position of the source is influenced by various factors such as noise and reverberation, leading to significant uncertainty. Quantifying this uncertainty is essential, particularly when localization outcomes impact critical decision-making processes, such as in robot audition, where the accuracy of location estimates directly influences subsequent actions. Despite this, many localization methods typically offer point estimates without quantifying the estimation uncertainty. To address this, we employ conformal prediction (CP)-a framework that delivers statistically valid prediction intervals with finite-sample guarantees, independent of the data distribution. However, commonly used Inductive CP (ICP) methods require a substantial amount of labeled data, which can be difficult to obtain in the localization setting. To mitigate this limitation, we incorporate a manifold-based localization method using Gaussian process regression (GPR), with an efficient Transductive CP (TCP) technique specifically designed for GPR. We demonstrate that our method generates statistically valid uncertainty intervals across different acoustic conditions.

This work presents a novel approach to monocular 6D pose estimation of surgical instruments in open surgery, addressing challenges such as object articulations, symmetries, occlusions, and lack of annotated real-world data. The method leverages synthetic data generation and domain adaptation techniques to overcome these obstacles. The proposed approach consists of three main components: (1) synthetic data generation using 3D modeling of surgical tools with articulation rigging and physically-based rendering; (2) a tailored pose estimation framework combining object detection with pose estimation and a hybrid geometric fusion strategy; and (3) a training strategy that utilizes both synthetic and real unannotated data, employing domain adaptation on real video data using automatically generated pseudo-labels. Evaluations conducted on videos of open surgery demonstrate the good performance and real-world applicability of the proposed method, highlighting its potential for integration into medical augmented reality and robotic systems. The approach eliminates the need for extensive manual annotation of real surgical data.

Surgical phase recognition is a key task in computer-assisted surgery, aiming to automatically identify and categorize the different phases within a surgical procedure. Despite substantial advancements, most current approaches rely on fully supervised training, requiring expensive and time-consuming frame-level annotations. Timestamp supervision has recently emerged as a promising alternative, significantly reducing annotation costs while maintaining competitive performance. However, models trained on timestamp annotations can be negatively impacted by missing phase annotations, leading to a potential drawback in real-world scenarios. In this work, we address this issue by proposing a robust method for surgical phase recognition that can handle missing phase annotations effectively. Furthermore, we introduce the SkipTag@K annotation approach to the surgical domain, enabling a flexible balance between annotation effort and model performance. Our method achieves competitive results on two challenging datasets, demonstrating its efficacy in handling missing phase annotations and its potential for reducing annotation costs. Specifically, we achieve an accuracy of 85.1\% on the MultiBypass140 dataset using only 3 annotated frames per video, showcasing the effectiveness of our method and the potential of the SkipTag@K setup. We perform extensive experiments to validate the robustness of our method and provide valuable insights to guide future research in surgical phase recognition. Our work contributes to the advancement of surgical workflow recognition and paves the way for more efficient and reliable surgical phase recognition systems.

Proteins are essential for almost all biological processes and derive their diverse functions from complex 3D structures, which are in turn determined by their amino acid sequences. In this paper, we exploit the rich biological inductive bias of amino acid sequences and introduce FoldFlow-2, a novel sequence-conditioned SE(3)-equivariant flow matching model for protein structure generation. FoldFlow-2 presents substantial new architectural features over the previous FoldFlow family of models including a protein large language model to encode sequence, a new multi-modal fusion trunk that combines structure and sequence representations, and a geometric transformer based decoder. To increase diversity and novelty of generated samples -- crucial for de-novo drug design -- we train FoldFlow-2 at scale on a new dataset that is an order of magnitude larger than PDB datasets of prior works, containing both known proteins in PDB and high-quality synthetic structures achieved through filtering. We further demonstrate the ability to align FoldFlow-2 to arbitrary rewards, e.g. increasing secondary structures diversity, by introducing a Reinforced Finetuning (ReFT) objective. We empirically observe that FoldFlow-2 outperforms previous state-of-the-art protein structure-based generative models, improving over RFDiffusion in terms of unconditional generation across all metrics including designability, diversity, and novelty across all protein lengths, as well as exhibiting generalization on the task of equilibrium conformation sampling. Finally, we demonstrate that a fine-tuned FoldFlow-2 makes progress on challenging conditional design tasks such as designing scaffolds for the VHH nanobody., Comment: preprint

This work addresses the scattering problem of an incident wave at a junction connecting two semi-infinite waveguides, which we intend to solve using Physics-Informed Neural Networks (PINNs). As with other deep learning-based approaches, PINNs are known to suffer from a spectral bias and from the hyperbolic nature of the Helmholtz equation. This makes the training process challenging, especially for higher wave numbers. We show an example where these limitations are present. In order to improve the learning capability of our model, we suggest an equivalent formulation of the Helmholtz Boundary Value Problem (BVP) that is based on splitting the total wave into a tapered continuation of the incoming wave and a remaining scattered wave. This allows the introduction of an inhomogeneity in the BVP, leveraging the information transmitted during back-propagation, thus, enhancing and accelerating the training process of our PINN model. The presented numerical illustrations are in accordance with the expected behavior, paving the way to a possible alternative approach to predicting scattering problems using PINNs.

In this paper, we introduce VoteCut, an innovative method for unsupervised object discovery that leverages feature representations from multiple self-supervised models. VoteCut employs normalized-cut based graph partitioning, clustering and a pixel voting approach. Additionally, We present CuVLER (Cut-Vote-and-LEaRn), a zero-shot model, trained using pseudo-labels, generated by VoteCut, and a novel soft target loss to refine segmentation accuracy. Through rigorous evaluations across multiple datasets and several unsupervised setups, our methods demonstrate significant improvements in comparison to previous state-of-the-art models. Our ablation studies further highlight the contributions of each component, revealing the robustness and efficacy of our approach. Collectively, VoteCut and CuVLER pave the way for future advancements in image segmentation., Comment: Accepted to CVPR 2024

This paper presents DiffMoog - a differentiable modular synthesizer with a comprehensive set of modules typically found in commercial instruments. Being differentiable, it allows integration into neural networks, enabling automated sound matching, to replicate a given audio input. Notably, DiffMoog facilitates modulation capabilities (FM/AM), low-frequency oscillators (LFOs), filters, envelope shapers, and the ability for users to create custom signal chains. We introduce an open-source platform that comprises DiffMoog and an end-to-end sound matching framework. This framework utilizes a novel signal-chain loss and an encoder network that self-programs its outputs to predict DiffMoogs parameters based on the user-defined modular architecture. Moreover, we provide insights and lessons learned towards sound matching using differentiable synthesis. Combining robust sound capabilities with a holistic platform, DiffMoog stands as a premier asset for expediting research in audio synthesis and machine learning., Comment: 5 pages, 7 figures, 1 table, Our code is released at https://github.com/aisynth/diffmoog

The ability to locate and classify action segments in long untrimmed video is of particular interest to many applications such as autonomous cars, robotics and healthcare applications. Today, the most popular pipeline for action segmentation is composed of encoding the frames into feature vectors, which are then processed by a temporal model for segmentation. In this paper we present a self-supervised method that comes in the middle of the standard pipeline and generated refined representations of the original feature vectors. Experiments show that this method improves the performance of existing models on different sub-tasks of action segmentation, even without additional hyper parameter tuning.

With the rapid growth of the developer community, the amount of posts on online technical forums has been growing rapidly, which poses difficulties for users to filter useful posts and find important information. Tags provide a concise feature dimension for users to locate their interested posts and for search engines to index the most relevant posts according to the queries. However, most tags are only focused on the technical perspective (e.g., program language, platform, tool). In most cases, forum posts in online developer communities reveal the author's intentions to solve a problem, ask for advice, share information, etc. The modeling of the intentions of posts can provide an extra dimension to the current tag taxonomy. By referencing previous studies and learning from industrial perspectives, we create a refined taxonomy for the intentions of technical forum posts. Through manual labeling and analysis on a sampled post dataset extracted from online forums, we understand the relevance between the constitution of posts (code, error messages) and their intentions. Furthermore, inspired by our manual study, we design a pre-trained transformer-based model to automatically predict post intentions. The best variant of our intention prediction framework, which achieves a Micro F1-score of 0.589, Top 1-3 accuracy of 62.6% to 87.8%, and an average AUC of 0.787, outperforms the state-of-the-art baseline approach. Our characterization and automated classification of forum posts regarding their intentions may help forum maintainers or third-party tool developers improve the organization and retrieval of posts on technical forums. We have released our annotated dataset and codes in our supplementary material package., Comment: Journal of Empirical Software Engineering, 40 pages

Adjustable hyperparameters of machine learning models typically impact various key trade-offs such as accuracy, fairness, robustness, or inference cost. Our goal in this paper is to find a configuration that adheres to user-specified limits on certain risks while being useful with respect to other conflicting metrics. We solve this by combining Bayesian Optimization (BO) with rigorous risk-controlling procedures, where our core idea is to steer BO towards an efficient testing strategy. Our BO method identifies a set of Pareto optimal configurations residing in a designated region of interest. The resulting candidates are statistically verified and the best-performing configuration is selected with guaranteed risk levels. We demonstrate the effectiveness of our approach on a range of tasks with multiple desiderata, including low error rates, equitable predictions, handling spurious correlations, managing rate and distortion in generative models, and reducing computational costs.

A broad current application of algorithms is in formal and quantitative measures of murky concepts -- like merit -- to make decisions. When people strategically respond to these sorts of evaluations in order to gain favorable decision outcomes, their behavior can be subjected to moral judgments. They may be described as 'gaming the system' or 'cheating,' or (in other cases) investing 'honest effort' or 'improving.' Machine learning literature on strategic behavior has tried to describe these dynamics by emphasizing the efforts expended by decision subjects hoping to obtain a more favorable assessment -- some works offer ways to preempt or prevent such manipulations, some differentiate 'gaming' from 'improvement' behavior, while others aim to measure the effort burden or disparate effects of classification systems. We begin from a different starting point: that the design of an evaluation itself can be understood as furthering goals held by the evaluator which may be misaligned with broader societal goals. To develop the idea that evaluation represents a strategic interaction in which both the evaluator and the subject of their evaluation are operating out of self-interest, we put forward a model that represents the process of evaluation using three interacting agents: a decision subject, an evaluator, and society, representing a bundle of values and oversight mechanisms. We highlight our model's applicability to a number of social systems where one or two players strategically undermine the others' interests to advance their own. Treating evaluators as themselves strategic allows us to re-cast the scrutiny directed at decision subjects, towards the incentives that underpin institutional designs of evaluations. The moral standing of strategic behaviors often depend on the moral standing of the evaluations and incentives that provoke such behaviors., Comment: 12 pages, 2 figures, EAAMO 2023

Deep Reinforcement Learning (Deep RL) is increasingly used to cope with the open-world assumption in service-oriented systems. Deep RL was successfully applied to problems such as dynamic service composition, job scheduling, and offloading, as well as service adaptation. While Deep RL offers many benefits, understanding the decision-making of Deep RL is challenging because its learned decision-making policy essentially appears as a black box. Yet, understanding the decision-making of Deep RL is key to help service developers perform debugging, support service providers to comply with relevant legal frameworks, and facilitate service users to build trust. We introduce Chat4XAI to facilitate the understanding of the decision-making of Deep RL by providing natural-language explanations. Compared with visual explanations, the reported benefits of natural-language explanations include better understandability for non-technical users, increased user acceptance and trust, as well as more efficient explanations. Chat4XAI leverages modern AI chatbot technology and dedicated prompt engineering. Compared to earlier work on natural-language explanations using classical software-based dialogue systems, using an AI chatbot eliminates the need for eliciting and defining potential questions and answers up-front. We prototypically realize Chat4XAI using OpenAI's ChatGPT API and evaluate the fidelity and stability of its explanations using an adaptive service exemplar., Comment: To be published at 21st Int'l Conference on Service-Oriented Computing (ICSOC 2023), Rome, Italy, November 28-December 1, 2023, ser. LNCS, F. Monti, S. Rinderle-Ma, A. Ruiz Cortes, Z. Zheng, M. Mecella, Eds., Springer, 2023

Patient's vital signs, which are displayed on monitors, make the anesthesiologist's visual attention (VA) a key component in the safe management of patients under general anesthesia; moreover, the distribution of said VA and the ability to acquire specific cues throughout the anesthetic, may have a direct impact on patient's outcome. Currently, most studies employ wearable eye-tracking technologies to analyze anesthesiologists' visual patterns. Albeit being able to produce meticulous data, wearable devices are not a sustainable solution for large-scale or long-term use for data collection in the operating room (OR). Thus, by utilizing a novel eye-tracking method in the form of deep learning models that process monitor-mounted webcams, we collected continuous behavioral data and gained insight into the anesthesiologist's VA distribution with minimal disturbance to their natural workflow. In this study, we collected OR video recordings using the proposed framework and compared different visual behavioral patterns. We distinguished between baseline VA distribution during uneventful periods to patterns associated with active phases or during critical, unanticipated incidents. In the future, such a platform may serve as a crucial component of context-aware assistive technologies in the OR., Comment: Submitted to MICCAI Aml4HC 2023

Major advances in Machine Learning (ML) and Artificial Intelligence (AI) increasingly take the form of developing and releasing general-purpose models. These models are designed to be adapted by other businesses and agencies to perform a particular, domain-specific function. This process has become known as adaptation or fine-tuning. This paper offers a model of the fine-tuning process where a Generalist brings the technological product (here an ML model) to a certain level of performance, and one or more Domain-specialist(s) adapts it for use in a particular domain. Both entities are profit-seeking and incur costs when they invest in the technology, and they must reach a bargaining agreement on how to share the revenue for the technology to reach the market. For a relatively general class of cost and revenue functions, we characterize the conditions under which the fine-tuning game yields a profit-sharing solution. We observe that any potential domain-specialization will either contribute, free-ride, or abstain in their uptake of the technology, and we provide conditions yielding these different strategies. We show how methods based on bargaining solutions and sub-game perfect equilibria provide insights into the strategic behavior of firms in these types of interactions, and we find that profit-sharing can still arise even when one firm has significantly higher costs than another. We also provide methods for identifying Pareto-optimal bargaining arrangements for a general set of utility functions., Comment: 36 pages, 8 figures

Online reinforcement learning (RL) is increasingly used for realizing adaptive systems in the presence of design time uncertainty. Online RL facilitates learning from actual operational data and thereby leverages feedback only available at runtime. However, Online RL requires the definition of an effective and correct reward function, which quantifies the feedback to the RL algorithm and thereby guides learning. With Deep RL gaining interest, the learned knowledge is no longer explicitly represented, but is represented as a neural network. For a human, it becomes practically impossible to relate the parametrization of the neural network to concrete RL decisions. Deep RL thus essentially appears as a black box, which severely limits the debugging of adaptive systems. We previously introduced the explainable RL technique XRL-DINE, which provides visual insights into why certain decisions were made at important time points. Here, we introduce an empirical user study involving 54 software engineers from academia and industry to assess (1) the performance of software engineers when performing different tasks using XRL-DINE and (2) the perceived usefulness and ease of use of XRL-DINE., Comment: arXiv admin note: substantial text overlap with arXiv:2210.05931

The advent of ChatGPT by OpenAI has prompted extensive discourse on its potential implications for science and higher education. While the impact on education has been a primary focus, there is limited empirical research on the effects of large language models (LLMs) and LLM-based chatbots on science and scientific practice. To investigate this further, we conducted a Delphi study involving 72 experts specialising in research and AI. The study focused on applications and limitations of LLMs, their effects on the science system, ethical and legal considerations, and the required competencies for their effective use. Our findings highlight the transformative potential of LLMs in science, particularly in administrative, creative, and analytical tasks. However, risks related to bias, misinformation, and quality assurance need to be addressed through proactive regulation and science education. This research contributes to informed discussions on the impact of generative AI in science and helps identify areas for future action., Comment: 31 pages, 2 figures

Biomedical photoacoustic (PA) imaging is typically used to exploit absorption-based contrast in soft tissue at depths of several centimeters. When it is applied to measuring PA waves generated in the brain, the acoustic properties of the skull bone cause not only strong attenuation but also a distortion of the wavefront, which diminishes image resolution and contrast. This effect is directly proportional to bone thickness. As a result, transcranial PA imaging in humans has been challenging to demonstrate. We measured the acoustic constraints imposed by the human skull to design an ultrasound sensor suitable for transcranial PA imaging and sensing. We imaged the phantoms using a planar Fabry-Perot sensor and employed a range of piezoelectric and optical ultrasound sensors to measure the frequency dependent acoustic transmission through human cranial bone. Transcranial PA images show typical frequency and thickness dependent attenuation and aberration effects associated with acoustic propagation through bone. The skull insertion loss measurements showed significant transmission at low frequencies. In comparison to conventional piezoelectric sensors, the performance of plano-concave optical resonator (PCOR) ultrasound sensors was found to be highly suitable for transcranial PA measurements. They possess high acoustic sensitivity at a low acoustic frequency range that coincides with the transmission window of human skull bone. PCOR sensors showed low noise equivalent pressures and flat frequency response which enabled them to outperform conventional piezoelectric transducers in transcranial PA sensing experiments. Transcranial PA sensing and imaging requires ultrasound sensors with high sensitivity at low acoustic frequencies, and a broad and ideally uniform frequency response. We designed and fabricated PCOR sensors and demonstrated their suitability for transcranial PA sensing.

Optimization is offered as an objective approach to resolving complex, real-world decisions involving uncertainty and conflicting interests. It drives business strategies as well as public policies and, increasingly, lies at the heart of sophisticated machine learning systems. A paradigm used to approach potentially high-stakes decisions, optimization relies on abstracting the real world to a set of decision(s), objective(s) and constraint(s). Drawing from the modeling process and a range of actual cases, this paper describes the normative choices and assumptions that are necessarily part of using optimization. It then identifies six emergent problems that may be neglected: 1) Misspecified values can yield optimizations that omit certain imperatives altogether or incorporate them incorrectly as a constraint or as part of the objective, 2) Problematic decision boundaries can lead to faulty modularity assumptions and feedback loops, 3) Failing to account for multiple agents' divergent goals and decisions can lead to policies that serve only certain narrow interests, 4) Mislabeling and mismeasurement can introduce bias and imprecision, 5) Faulty use of relaxation and approximation methods, unaccompanied by formal characterizations and guarantees, can severely impede applicability, and 6) Treating optimization as a justification for action, without specifying the necessary contextual information, can lead to ethically dubious or faulty decisions. Suggestions are given to further understand and curb the harms that can arise when optimization is used wrongfully., Comment: 14 pages, 1 figure, presentation at FAccT23

With the approach of Exascale computing power for large-scale High Performance Computing (HPC) clusters, the gap between compute capabilities and storage systems is growing larger. This is particularly problematic for the Weather Research and Forecasting Model (WRF), a widely-used HPC application for high-resolution forecasting and research that produces sizable datasets, especially when analyzing transient weather phenomena. Despite this issue, the I/O modules within WRF have not been updated in the past ten years, resulting in subpar parallel I/O performance. This research paper demonstrates the positive impact of integrating ADIOS2, a next-generation parallel I/O framework, as a new I/O backend option in WRF. It goes into detail about the challenges encountered during the integration process and how they were addressed. The resulting I/O times show an over tenfold improvement when using ADIOS2 compared to traditional MPI-I/O based solutions. Furthermore, the study highlights the new features available to WRF users worldwide, such as the Sustainable Staging Transport (SST) enabling Unified Communication X (UCX) DataTransport, the node-local burst buffer write capabilities and in-line lossless compression capabilities of ADIOS2. Additionally, the research shows how ADIOS2's in-situ analysis capabilities can be smoothly integrated with a simple WRF forecasting pipeline, resulting in a significant improvement in overall time to solution. This study serves as a reminder to legacy HPC applications that incorporating modern libraries and tools can lead to considerable performance enhancements with minimal changes to the core application., Comment: arXiv admin note: text overlap with arXiv:2201.08228

Action segmentation is a challenging task in high-level process analysis, typically performed on video or kinematic data obtained from various sensors. This work presents two contributions related to action segmentation on kinematic data. Firstly, we introduce two versions of Multi-Stage Temporal Convolutional Recurrent Networks (MS-TCRNet), specifically designed for kinematic data. The architectures consist of a prediction generator with intra-stage regularization and Bidirectional LSTM or GRU-based refinement stages. Secondly, we propose two new data augmentation techniques, World Frame Rotation and Hand Inversion, which utilize the strong geometric structure of kinematic data to improve algorithm performance and robustness. We evaluate our models on three datasets of surgical suturing tasks: the Variable Tissue Simulation (VTS) Dataset and the newly introduced Bowel Repair Simulation (BRS) Dataset, both of which are open surgery simulation datasets collected by us, as well as the JHU-ISI Gesture and Skill Assessment Working Set (JIGSAWS), a well-known benchmark in robotic surgery. Our methods achieved state-of-the-art performance., Comment: 41 pages, 7 figures. Submitted to Pattern Recognition