Search

A key motivation in the development of distributed Model Predictive Control (MPC) is to widen the computational bottleneck of centralized MPC for large-scale systems. Parallelizing computations among individual subsystems, distributed MPC has the prospect of scaling well for large networks. However, the communication demand may deteriorate the performance of iterative decentralized optimization, if excessively many optimizer iterations are required per control step. Moreover, centralized solvers often exhibit faster asymptotic convergence rates and, by parallelizing costly linear algebra operations, they can also benefit from modern multi-core computing architectures. On this canvas, we study the computational performance of cooperative distributed MPC for linear and nonlinear systems. To this end, we apply a tailored decentralized real-time iteration scheme to frequency control for power systems. For the considered linear and nonlinear benchmarks, distributed MPC and distributed Nonlinear MPC (NMPC) scale well as the required number of iterations does not depend on the number of subsystems. Comparisons with multithreaded centralized solvers show competitive performance of the considered decentralized optimization algorithms.

Search query suggestions affect users' interactions with search engines, which then influences the information they encounter. Thus, bias in search query suggestions can lead to exposure to biased search results and can impact opinion formation. This is especially critical in the political domain. Detecting and quantifying bias in web search engines is difficult due to its topic dependency, complexity, and subjectivity. The lack of context and phrasality of query suggestions emphasizes this problem. In a multi-step approach, we combine the benefits of large language models, pairwise comparison, and Elo-based scoring to identify and quantify bias in English search query suggestions. We apply our approach to the U.S. political news domain and compare bias in Google and Bing.

The performance of neural networks scales with both their size and the amount of data they have been trained on. This is shown in both language and image generation. However, this requires scaling-friendly network architectures as well as large-scale datasets. Even though scaling-friendly architectures like transformers have emerged for 3D vision tasks, the GPT-moment of 3D vision remains distant due to the lack of training data. In this paper, we introduce ARKit LabelMaker, the first large-scale, real-world 3D dataset with dense semantic annotations. Specifically, we complement ARKitScenes dataset with dense semantic annotations that are automatically generated at scale. To this end, we extend LabelMaker, a recent automatic annotation pipeline, to serve the needs of large-scale pre-training. This involves extending the pipeline with cutting-edge segmentation models as well as making it robust to the challenges of large-scale processing. Further, we push forward the state-of-the-art performance on ScanNet and ScanNet200 dataset with prevalent 3D semantic segmentation models, demonstrating the efficacy of our generated dataset.

Open-vocabulary 3D segmentation enables the exploration of 3D spaces using free-form text descriptions. Existing methods for open-vocabulary 3D instance segmentation primarily focus on identifying object-level instances in a scene. However, they face challenges when it comes to understanding more fine-grained scene entities such as object parts, or regions described by generic attributes. In this work, we introduce Search3D, an approach that builds a hierarchical open-vocabulary 3D scene representation, enabling the search for entities at varying levels of granularity: fine-grained object parts, entire objects, or regions described by attributes like materials. Our method aims to expand the capabilities of open vocabulary instance-level 3D segmentation by shifting towards a more flexible open-vocabulary 3D search setting less anchored to explicit object-centric queries, compared to prior work. To ensure a systematic evaluation, we also contribute a scene-scale open-vocabulary 3D part segmentation benchmark based on MultiScan, along with a set of open-vocabulary fine-grained part annotations on ScanNet++. We verify the effectiveness of Search3D across several tasks, demonstrating that our approach outperforms baselines in scene-scale open-vocabulary 3D part segmentation, while maintaining strong performance in segmenting 3D objects and materials., Comment: This work has been submitted to the IEEE for possible publication

Taking part in surveys, experiments, and studies is often compensated by rewards to increase the number of participants and encourage attendance. While privacy requirements are usually considered for participation, privacy aspects of the reward procedure are mostly ignored. To this end, we introduce PrePaMS, an efficient participation management system that supports prerequisite checks and participation rewards in a privacy-preserving way. Our system organizes participations with potential (dis-)qualifying dependencies and enables secure reward payoffs. By leveraging a set of proven cryptographic primitives and mechanisms such as anonymous credentials and zero-knowledge proofs, participations are protected so that service providers and organizers cannot derive the identity of participants even within the reward process. In this paper, we have designed and implemented a prototype of PrePaMS to show its effectiveness and evaluated its performance under realistic workloads. PrePaMS covers the information whether subjects have participated in surveys, experiments, or studies. When combined with other secure solutions for the actual data collection within these events, PrePaMS can represent a cornerstone for more privacy-preserving empirical research., Comment: Prototype source code: https://github.com/vs-uulm/prepams/ Public test deployment: https://vs-uulm.github.io/prepams/

In this work, we tackle the task of point cloud denoising through a novel framework that adapts Diffusion Schr\"odinger bridges to points clouds. Unlike previous approaches that predict point-wise displacements from point features or learned noise distributions, our method learns an optimal transport plan between paired point clouds. Experiments on object datasets like PU-Net and real-world datasets such as ScanNet++ and ARKitScenes show that P2P-Bridge achieves significant improvements over existing methods. While our approach demonstrates strong results using only point coordinates, we also show that incorporating additional features, such as color information or point-wise DINOv2 features, further enhances the performance. Code and pretrained models are available at https://p2p-bridge.github.io., Comment: ECCV 2024 Project page: https://p2p-bridge.github.io

Current visual foundation models are trained purely on unstructured 2D data, limiting their understanding of 3D structure of objects and scenes. In this work, we show that fine-tuning on 3D-aware data improves the quality of emerging semantic features. We design a method to lift semantic 2D features into an efficient 3D Gaussian representation, which allows us to re-render them for arbitrary views. Using the rendered 3D-aware features, we design a fine-tuning strategy to transfer such 3D awareness into a 2D foundation model. We demonstrate that models fine-tuned in that way produce features that readily improve downstream task performance in semantic segmentation and depth estimation through simple linear probing. Notably, though fined-tuned on a single indoor dataset, the improvement is transferable to a variety of indoor datasets and out-of-domain datasets. We hope our study encourages the community to consider injecting 3D awareness when training 2D foundation models. Project page: https://ywyue.github.io/FiT3D., Comment: ECCV 2024. Project page: https://ywyue.github.io/FiT3D

Purpose: To describe OCTolyzer: an open-source toolkit for retinochoroidal analysis in optical coherence tomography (OCT) and scanning laser ophthalmoscopy (SLO) images. Method: OCTolyzer has two analysis suites, for SLO and OCT images. The former enables anatomical segmentation and feature measurement of the en face retinal vessels. The latter leverages image metadata for retinal layer segmentations and deep learning-based choroid layer segmentation to compute retinochoroidal measurements such as thickness and volume. We introduce OCTolyzer and assess the reproducibility of its OCT analysis suite for choroid analysis. Results: At the population-level, choroid region metrics were highly reproducible (Mean absolute error/Pearson/Spearman correlation for macular volume choroid thickness (CT):6.7$\mu$m/0.9933/0.9969, macular B-scan CT:11.6$\mu$m/0.9858/0.9889, peripapillary CT:5.0$\mu$m/0.9942/0.9940). Macular choroid vascular index (CVI) had good reproducibility (volume CVI:0.0271/0.9669/0.9655, B-scan CVI:0.0130/0.9090/0.9145). At the eye-level, measurement error in regional and vessel metrics were below 5% and 20% of the population's variability, respectively. Major outliers were from poor quality B-scans with thick choroids and invisible choroid-sclera boundary. Conclusions: OCTolyzer is the first open-source pipeline to convert OCT/SLO data into reproducible and clinically meaningful retinochoroidal measurements. OCT processing on a standard laptop CPU takes under 2 seconds for macular or peripapillary B-scans and 85 seconds for volume scans. OCTolyzer can help improve standardisation in the field of OCT/SLO image analysis and is freely available here: https://github.com/jaburke166/OCTolyzer., Comment: Main paper: 15 pages, 8 figures, 3 tables. Supplementary material: 6 pages, 6 figures, 6 tables. Submitted to "New Frontiers in Optical Coherence Tomography" Special Issue at ARVO Translational Vision Science & Technology

Purpose: The purpose of this study was to introduce SLOctolyzer: an open-source analysis toolkit for en face retinal vessels in infrared reflectance scanning laser ophthalmoscopy (SLO) images. Methods: SLOctolyzer includes two main modules: segmentation and measurement. The segmentation module uses deep learning methods to delineate retinal anatomy, and detects the fovea and optic disc, whereas the measurement module quantifies the complexity, density, tortuosity, and calibre of the segmented retinal vessels. We evaluated the segmentation module using unseen data and measured its reproducibility. Results: SLOctolyzer's segmentation module performed well against unseen internal test data (Dice for all-vessels = 0.91; arteries = 0.84; veins = 0.85; optic disc = 0.94; and fovea = 0.88). External validation against severe retinal pathology showed decreased performance (Dice for arteries = 0.72; veins = 0.75; and optic disc = 0.90). SLOctolyzer had good reproducibility (mean difference for fractal dimension = -0.001; density = -0.0003; calibre = -0.32 microns; and tortuosity density = 0.001). SLOctolyzer can process a 768 x 768 pixel macula-centred SLO image in under 20 seconds and a disc-centred SLO image in under 30 seconds using a laptop CPU. Conclusions: To our knowledge, SLOctolyzer is the first open-source tool to convert raw SLO images into reproducible and clinically meaningful retinal vascular parameters. SLO images are captured simultaneous to optical coherence tomography (OCT), and we believe SLOctolyzer will be useful for extracting retinal vascular measurements from large OCT image sets and linking them to ocular or systemic diseases. It requires no specialist knowledge or proprietary software, and allows manual correction of segmentations and re-computing of vascular metrics. SLOctolyzer is freely available at https://github.com/jaburke166/SLOctolyzer., Comment: 13 pages, 6 figures, 6 tables + Supplementary (9 pages, 13 figures, 4 tables, 2 code listings). Accepted and published at ARVO Translational Vision Science and Technology

Education plays an indispensable role in fostering societal well-being and is widely regarded as one of the most influential factors in shaping the future of generations to come. As artificial intelligence (AI) becomes more deeply integrated into our daily lives and the workforce, educational institutions at all levels are directing their focus on resources that cater to AI education. Our work investigates the current landscape of introductory AI courses on YouTube, and the potential for introducing ethics in this context. We qualitatively analyze the 20 most watched introductory AI courses on YouTube, coding a total of 92.2 hours of educational content viewed by close to 50 million people. Introductory AI courses do not meaningfully engage with ethical or societal challenges of AI (RQ1). When \textit{defining and framing AI}, introductory AI courses foreground excitement around AI's transformative role in society, over-exaggerate AI's current and future abilities, and anthropomorphize AI (RQ2). In \textit{teaching AI}, we see a widespread reliance on corporate AI tools and frameworks as well as a prioritization on a hands-on approach to learning rather than on conceptual foundations (RQ3). In promoting key \textit{AI practices}, introductory AI courses abstract away entirely the socio-technical nature of AI classification and prediction, for example by favoring data quantity over data quality (RQ4). We extend our analysis with recommendations that aim to integrate ethical reflections into introductory AI courses. We recommend that introductory AI courses should (1) highlight ethical challenges of AI to present a more balanced perspective, (2) raise ethical issues explicitly relevant to the technical concepts discussed and (3) nurture a sense of accountability in future AI developers.

Recently, Vision-Language Models (VLMs) have advanced segmentation techniques by shifting from the traditional segmentation of a closed-set of predefined object classes to open-vocabulary segmentation (OVS), allowing users to segment novel classes and concepts unseen during training of the segmentation model. However, this flexibility comes with a trade-off: fully-supervised closed-set methods still outperform OVS methods on base classes, that is on classes on which they have been explicitly trained. This is due to the lack of pixel-aligned training masks for VLMs (which are trained on image-caption pairs), and the absence of domain-specific knowledge, such as autonomous driving. Therefore, we propose the task of open-vocabulary domain adaptation to infuse domain-specific knowledge into VLMs while preserving their open-vocabulary nature. By doing so, we achieve improved performance in base and novel classes. Existing VLM adaptation methods improve performance on base (training) queries, but fail to fully preserve the open-set capabilities of VLMs on novel queries. To address this shortcoming, we combine parameter-efficient prompt tuning with a triplet-loss-based training strategy that uses auxiliary negative queries. Notably, our approach is the only parameter-efficient method that consistently surpasses the original VLM on novel classes. Our adapted VLMs can seamlessly be integrated into existing OVS pipelines, e.g., improving OVSeg by +6.0% mIoU on ADE20K for open-vocabulary 2D segmentation, and OpenMask3D by +4.1% AP on ScanNet++ Offices for open-vocabulary 3D instance segmentation without other changes. The project page is available at https://open-das.github.io/.

The choroid is a key vascular layer of the eye, supplying oxygen to the retinal photoreceptors. Non-invasive enhanced depth imaging optical coherence tomography (EDI-OCT) has recently improved access and visualisation of the choroid, making it an exciting frontier for discovering novel vascular biomarkers in ophthalmology and wider systemic health. However, current methods to measure the choroid often require use of multiple, independent semi-automatic and deep learning-based algorithms which are not made open-source. Previously, Choroidalyzer -- an open-source, fully automatic deep learning method trained on 5,600 OCT B-scans from 385 eyes -- was developed to fully segment and quantify the choroid in EDI-OCT images, thus addressing these issues. Using the same dataset, we propose a Robust, Resolution-agnostic and Efficient Attention-based network for CHoroid segmentation (REACH). REACHNet leverages multi-resolution training with domain-specific data augmentation to promote generalisation, and uses a lightweight architecture with resolution-agnostic self-attention which is not only faster than Choroidalyzer's previous network (4 images/s vs. 2.75 images/s on a standard laptop CPU), but has greater performance for segmenting the choroid region, vessels and fovea (Dice coefficient for region 0.9769 vs. 0.9749, vessels 0.8612 vs. 0.8192 and fovea 0.8243 vs. 0.3783) due to its improved hyperparameter configuration and model training pipeline. REACHNet can be used with Choroidalyzer as a drop-in replacement for the original model and will be made available upon publication., Comment: 13 pages, 2 figures, 8 tables (including supplementary material)

Artificial Intelligence in medicine is traditionally limited by the lack of massive training datasets. Foundation models, pre-trained models that can be adapted to downstream tasks with small datasets, could alleviate this problem. Researchers at Moorfields Eye Hospital (MEH) proposed RETFound-MEH, a retinal foundation model trained on 900,000 images, including private hospital data. Recently, data-efficient DERETFound was proposed providing comparable performance while being trained on only 150,000 publicly available images. However, both these models required very substantial resources to train initially and are resource-intensive in downstream use. We propose a novel Token Reconstruction objective that we use to train RETFound-Green, a retinal foundation model trained using only 75,000 publicly available images and 400 times less compute. We estimate the cost of training RETFound-MEH and DERETFound at \$10,000 and \$14,000, respectively. RETFound-Green could be trained for less than \$100, with equally reduced environmental impact. RETFound-Green is also far more efficient in downstream use: it can be downloaded 14 times faster, computes vector embeddings 2.7 times faster which then require 2.6 times less storage space. Despite this, RETFound-Green does not perform systematically worse. In fact, on various task on three downstream datasets from Brazil, India and China, it performs best on 68 tasks out of 119 comparisons, versus 21 for DERETFound and 13 for RETFound-MEH. Our results suggest that RETFound-Green is a very efficient, high-performance retinal foundation model. We anticipate that our Token Reconstruction objective could be scaled up for even higher performance and be applied to other domains beyond retinal imaging.

In recent years, modern techniques in deep learning and large-scale datasets have led to impressive progress in 3D instance segmentation, grasp pose estimation, and robotics. This allows for accurate detection directly in 3D scenes, object- and environment-aware grasp prediction, as well as robust and repeatable robotic manipulation. This work aims to integrate these recent methods into a comprehensive framework for robotic interaction and manipulation in human-centric environments. Specifically, we leverage 3D reconstructions from a commodity 3D scanner for open-vocabulary instance segmentation, alongside grasp pose estimation, to demonstrate dynamic picking of objects, and opening of drawers. We show the performance and robustness of our model in two sets of real-world experiments including dynamic object retrieval and drawer opening, reporting a 51% and 82% success rate respectively. Code of our framework as well as videos are available on: https://spot-compose.github.io/., Comment: Accepted at ICRA 2024 Workshops. Code and videos available at https://spot-compose.github.io/

Business Process Modeling projects often require formal process models as a central component. High costs associated with the creation of such formal process models motivated many different fields of research aimed at automated generation of process models from readily available data. These include process mining on event logs, and generating business process models from natural language texts. Research in the latter field is regularly faced with the problem of limited data availability, hindering both evaluation and development of new techniques, especially learning-based ones. To overcome this data scarcity issue, in this paper we investigate the application of data augmentation for natural language text data. Data augmentation methods are well established in machine learning for creating new, synthetic data without human assistance. We find that many of these methods are applicable to the task of business process information extraction, improving the accuracy of extraction. Our study shows, that data augmentation is an important component in enabling machine learning methods for the task of business process model generation from natural language text, where currently mostly rule-based systems are still state of the art. Simple data augmentation techniques improved the $F_1$ score of mention extraction by 2.9 percentage points, and the $F_1$ of relation extraction by $4.5$. To better understand how data augmentation alters human annotated texts, we analyze the resulting text, visualizing and discussing the properties of augmented textual data. We make all code and experiments results publicly available., Comment: Accepted at BPMDS 2024 (https://sites.google.com/view/bpmds/), to be printed

Large visual-language models (VLMs), like CLIP, enable open-set image segmentation to segment arbitrary concepts from an image in a zero-shot manner. This goes beyond the traditional closed-set assumption, i.e., where models can only segment classes from a pre-defined training set. More recently, first works on open-set segmentation in 3D scenes have appeared in the literature. These methods are heavily influenced by closed-set 3D convolutional approaches that process point clouds or polygon meshes. However, these 3D scene representations do not align well with the image-based nature of the visual-language models. Indeed, point cloud and 3D meshes typically have a lower resolution than images and the reconstructed 3D scene geometry might not project well to the underlying 2D image sequences used to compute pixel-aligned CLIP features. To address these challenges, we propose OpenNeRF which naturally operates on posed images and directly encodes the VLM features within the NeRF. This is similar in spirit to LERF, however our work shows that using pixel-wise VLM features (instead of global CLIP features) results in an overall less complex architecture without the need for additional DINO regularization. Our OpenNeRF further leverages NeRF's ability to render novel views and extract open-set VLM features from areas that are not well observed in the initial posed images. For 3D point cloud segmentation on the Replica dataset, OpenNeRF outperforms recent open-vocabulary methods such as LERF and OpenScene by at least +4.9 mIoU., Comment: ICLR 2024, Project page: https://opennerf.github.io

We introduce a novel problem, i.e., the localization of an input image within a multi-modal reference map represented by a database of 3D scene graphs. These graphs comprise multiple modalities, including object-level point clouds, images, attributes, and relationships between objects, offering a lightweight and efficient alternative to conventional methods that rely on extensive image databases. Given the available modalities, the proposed method SceneGraphLoc learns a fixed-sized embedding for each node (i.e., representing an object instance) in the scene graph, enabling effective matching with the objects visible in the input query image. This strategy significantly outperforms other cross-modal methods, even without incorporating images into the map embeddings. When images are leveraged, SceneGraphLoc achieves performance close to that of state-of-the-art techniques depending on large image databases, while requiring three orders-of-magnitude less storage and operating orders-of-magnitude faster. The code will be made public.

The mutual information (MI) of Poisson-type channels has been linked to a filtering problem since the 70s, but its evaluation for specific continuous-time, discrete-state systems remains a demanding task. As an advantage, Markov renewal processes (MrP) retain their renewal property under state space filtering. This offers a way to solve the filtering problem analytically for small systems. We consider a class of communication systems $X \to Y$ that can be derived from an MrP by a custom filtering procedure. For the subclasses, where (i) $Y$ is a renewal process or (ii) $(X,Y)$ belongs to a class of MrPs, we provide an evolution equation for finite transmission duration $T>0$ and limit theorems for $T \to \infty$ that facilitate simulation-free evaluation of the MI $\mathbb{I}(X_{[0,T]}; Y_{[0,T]})$ and its associated mutual information rate (MIR). In other cases, simulation cost is reduced to the marginal system $(X,Y)$ or $Y$. We show that systems with an additional $X$-modulating level $C$, which statically chooses between different processes $X_{[0,T]}(c)$, can naturally be included in our framework, thereby giving an expression for $\mathbb{I}(C; Y_{[0,T]})$. Our primary contribution is to apply the results of classical (Markov renewal) filtering theory in a novel manner to the problem of exactly computing the MI/MIR. The theoretical framework is showcased in an application to bacterial gene expression, where filtering is analytically tractable., Comment: 5 main pages, 1 main figure, 5 appendix pages, 3 appendix figures, Accepted at ISIT 2024 conference

Purpose: To investigate whether Fractal Dimension (FD)-based oculomics could be used for individual risk prediction by evaluating repeatability and robustness. Methods: We used two datasets: Caledonia, healthy adults imaged multiple times in quick succession for research (26 subjects, 39 eyes, 377 colour fundus images), and GRAPE, glaucoma patients with baseline and follow-up visits (106 subjects, 196 eyes, 392 images). Mean follow-up time was 18.3 months in GRAPE, thus it provides a pessimistic lower-bound as vasculature could change. FD was computed with DART and AutoMorph. Image quality was assessed with QuickQual, but no images were initially excluded. Pearson, Spearman, and Intraclass Correlation (ICC) were used for population-level repeatability. For individual-level repeatability, we introduce measurement noise parameter {\lambda} which is within-eye Standard Deviation (SD) of FD measurements in units of between-eyes SD. Results: In Caledonia, ICC was 0.8153 for DART and 0.5779 for AutoMorph, Pearson/Spearman correlation (first and last image) 0.7857/0.7824 for DART, and 0.3933/0.6253 for AutoMorph. In GRAPE, Pearson/Spearman correlation (first and next visit) was 0.7479/0.7474 for DART, and 0.7109/0.7208 for AutoMorph (all p<0.0001). Median {\lambda} in Caledonia without exclusions was 3.55\% for DART and 12.65\% for AutoMorph, and improved to up to 1.67\% and 6.64\% with quality-based exclusions, respectively. Quality exclusions primarily mitigated large outliers. Worst quality in an eye correlated strongly with {\lambda} (Pearson 0.5350-0.7550, depending on dataset and method, all p<0.0001). Conclusions: Repeatability was sufficient for individual-level predictions in heterogeneous populations. DART performed better on all metrics and might be able to detect small, longitudinal changes, highlighting the potential of robust methods.

This report provides an overview of the challenge hosted at the OpenSUN3D Workshop on Open-Vocabulary 3D Scene Understanding held in conjunction with ICCV 2023. The goal of this workshop series is to provide a platform for exploration and discussion of open-vocabulary 3D scene understanding tasks, including but not limited to segmentation, detection and mapping. We provide an overview of the challenge hosted at the workshop, present the challenge dataset, the evaluation methodology, and brief descriptions of the winning methods. For additional details, please see https://opensun3d.github.io/index_iccv23.html., Comment: Our OpenSUN3D workshop website for ICCV 2023: https://opensun3d.github.io/index_iccv23.html

Dehumanization is a mental process that enables the exclusion and ill treatment of a group of people. In this paper, we present two data sets of dehumanizing text, a large, automatically collected corpus and a smaller, manually annotated data set. Both data sets include a combination of political discourse and dialogue from movie subtitles. Our methods give us a broad and varied amount of dehumanization data to work with, enabling further exploratory analysis and automatic classification of dehumanization patterns. Both data sets will be publicly released.

This article presents a Real-Time Iteration (RTI) scheme for distributed Nonlinear Model Predictive Control (NMPC). The scheme transfers the well-known RTI approach, a key enabler for many industrial real-time NMPC implementations, to the setting of cooperative distributed control. At each sampling instant, one outer iteration of a bi-level decentralized Sequential Quadratic Programming (dSQP) method is applied to a centralized optimal control croblem. This ensures that real-time requirements are met and it facilitates cooperation between subsystems. Combining novel dSQP convergence results with RTI stability guarantees, we prove local exponential stability under standard assumptions on the MPC design with and without terminal constraints. The proposed scheme only requires neighbor-to-neighbor communication and avoids a central coordinator. A numerical example with coupled inverted pendulums demonstrates the efficacy of the approach.

Accurate grasping is the key to several robotic tasks including assembly and household robotics. Executing a successful grasp in a cluttered environment requires multiple levels of scene understanding: First, the robot needs to analyze the geometric properties of individual objects to find feasible grasps. These grasps need to be compliant with the local object geometry. Second, for each proposed grasp, the robot needs to reason about the interactions with other objects in the scene. Finally, the robot must compute a collision-free grasp trajectory while taking into account the geometry of the target object. Most grasp detection algorithms directly predict grasp poses in a monolithic fashion, which does not capture the composability of the environment. In this paper, we introduce an end-to-end architecture for object-centric grasping. The method uses pointcloud data from a single arbitrary viewing direction as an input and generates an instance-centric representation for each partially observed object in the scene. This representation is further used for object reconstruction and grasp detection in cluttered table-top scenes. We show the effectiveness of the proposed method by extensively evaluating it against state-of-the-art methods on synthetic datasets, indicating superior performance for grasping and reconstruction. Additionally, we demonstrate real-world applicability by decluttering scenes with varying numbers of objects., Comment: 7 pages, 5 figures

Current 3D scene segmentation methods are heavily dependent on manually annotated 3D training datasets. Such manual annotations are labor-intensive, and often lack fine-grained details. Importantly, models trained on this data typically struggle to recognize object classes beyond the annotated classes, i.e., they do not generalize well to unseen domains and require additional domain-specific annotations. In contrast, 2D foundation models demonstrate strong generalization and impressive zero-shot abilities, inspiring us to incorporate these characteristics from 2D models into 3D models. Therefore, we explore the use of image segmentation foundation models to automatically generate training labels for 3D segmentation. We propose Segment3D, a method for class-agnostic 3D scene segmentation that produces high-quality 3D segmentation masks. It improves over existing 3D segmentation models (especially on fine-grained masks), and enables easily adding new training data to further boost the segmentation performance -- all without the need for manual training labels., Comment: Project Page: http://segment3d.github.io

Simulating user interactions enables a more user-oriented evaluation of information retrieval (IR) systems. While user simulations are cost-efficient and reproducible, many approaches often lack fidelity regarding real user behavior. Most notably, current user models neglect the user's context, which is the primary driver of perceived relevance and the interactions with the search results. To this end, this work introduces the simulation of context-driven query reformulations. The proposed query generation methods build upon recent Large Language Model (LLM) approaches and consider the user's context throughout the simulation of a search session. Compared to simple context-free query generation approaches, these methods show better effectiveness and allow the simulation of more efficient IR sessions. Similarly, our evaluations consider more interaction context than current session-based measures and reveal interesting complementary insights in addition to the established evaluation protocols. We conclude with directions for future work and provide an entirely open experimental setup., Comment: Accepted at ECIR 2024 (Full Paper)

The ForMAX beamline at the MAX IV Laboratory provides multiscale and multimodal structural characterization of hierarchical materials in the nm to mm range by combining small- and wide-angle x-ray scattering with full-field microtomography. The modular design of the beamline is optimized for easy switching between different experimental modalities. The beamline has a special focus on the development of novel, fibrous materials from forest resources, but it is also well suited for studies within, e.g., food science and biomedical research., Comment: Accepted for publication in J. Synchrotron Rad

Purpose: To develop Choroidalyzer, an open-source, end-to-end pipeline for segmenting the choroid region, vessels, and fovea, and deriving choroidal thickness, area, and vascular index. Methods: We used 5,600 OCT B-scans (233 subjects, 6 systemic disease cohorts, 3 device types, 2 manufacturers). To generate region and vessel ground-truths, we used state-of-the-art automatic methods following manual correction of inaccurate segmentations, with foveal positions manually annotated. We trained a U-Net deep-learning model to detect the region, vessels, and fovea to calculate choroid thickness, area, and vascular index in a fovea-centred region of interest. We analysed segmentation agreement (AUC, Dice) and choroid metrics agreement (Pearson, Spearman, mean absolute error (MAE)) in internal and external test sets. We compared Choroidalyzer to two manual graders on a small subset of external test images and examined cases of high error. Results: Choroidalyzer took 0.299 seconds per image on a standard laptop and achieved excellent region (Dice: internal 0.9789, external 0.9749), very good vessel segmentation performance (Dice: internal 0.8817, external 0.8703) and excellent fovea location prediction (MAE: internal 3.9 pixels, external 3.4 pixels). For thickness, area, and vascular index, Pearson correlations were 0.9754, 0.9815, and 0.8285 (internal) / 0.9831, 0.9779, 0.7948 (external), respectively (all p<0.0001). Choroidalyzer's agreement with graders was comparable to the inter-grader agreement across all metrics. Conclusions: Choroidalyzer is an open-source, end-to-end pipeline that accurately segments the choroid and reliably extracts thickness, area, and vascular index. Especially choroidal vessel segmentation is a difficult and subjective task, and fully-automatic methods like Choroidalyzer could provide objectivity and standardisation.

We propose an online 3D semantic segmentation method that incrementally reconstructs a 3D semantic map from a stream of RGB-D frames. Unlike offline methods, ours is directly applicable to scenarios with real-time constraints, such as robotics or mixed reality. To overcome the inherent challenges of online methods, we make two main contributions. First, to effectively extract information from the input RGB-D video stream, we jointly estimate geometry and semantic labels per frame in 3D. A key focus of our approach is to reason about semantic entities both in the 2D input and the local 3D domain to leverage differences in spatial context and network architectures. Our method predicts 2D features using an off-the-shelf segmentation network. The extracted 2D features are refined by a lightweight 3D network to enable reasoning about the local 3D structure. Second, to efficiently deal with an infinite stream of input RGB-D frames, a subsequent network serves as a temporal expert predicting the incremental scene updates by leveraging 2D, 3D, and past information in a learned manner. These updates are then integrated into a global scene representation. Using these main contributions, our method can enable scenarios with real-time constraints and can scale to arbitrary scene sizes by processing and updating the scene only in a local region defined by the new measurement. Our experiments demonstrate improved results compared to existing online methods that purely operate in local regions and show that complementary sources of information can boost the performance. We provide a thorough ablation study on the benefits of different architectural as well as algorithmic design decisions. Our method yields competitive results on the popular ScanNet benchmark and SceneNN dataset.

Semantic annotations are indispensable to train or evaluate perception models, yet very costly to acquire. This work introduces a fully automated 2D/3D labeling framework that, without any human intervention, can generate labels for RGB-D scans at equal (or better) level of accuracy than comparable manually annotated datasets such as ScanNet. Our approach is based on an ensemble of state-of-the-art segmentation models and 3D lifting through neural rendering. We demonstrate the effectiveness of our LabelMaker pipeline by generating significantly better labels for the ScanNet datasets and automatically labelling the previously unlabeled ARKitScenes dataset. Code and models are available at https://labelmaker.org

Predicting patient features from single-cell data can help identify cellular states implicated in health and disease. Linear models and average cell type expressions are typically favored for this task for their efficiency and robustness, but they overlook the rich cell heterogeneity inherent in single-cell data. To address this gap, we introduce MixMIL, a framework integrating Generalized Linear Mixed Models (GLMM) and Multiple Instance Learning (MIL), upholding the advantages of linear models while modeling cell state heterogeneity. By leveraging predefined cell embeddings, MixMIL enhances computational efficiency and aligns with recent advancements in single-cell representation learning. Our empirical results reveal that MixMIL outperforms existing MIL models in single-cell datasets, uncovering new associations and elucidating biological mechanisms across different domains., Comment: AISTATS 2024 Oral, Code: https://github.com/AIH-SGML/MixMIL

Considering the multimodal signals of search items is beneficial for retrieval effectiveness. Especially in web table retrieval (WTR) experiments, accounting for multimodal properties of tables boosts effectiveness. However, it still remains an open question how the single modalities affect user experience in particular. Previous work analyzed WTR performance in ad-hoc retrieval benchmarks, which neglects interactive search behavior and limits the conclusion about the implications for real-world user environments. To this end, this work presents an in-depth evaluation of simulated interactive WTR search sessions as a more cost-efficient and reproducible alternative to real user studies. As a first of its kind, we introduce interactive query reformulation strategies based on Doc2Query, incorporating cognitive states of simulated user knowledge. Our evaluations include two perspectives on user effectiveness by considering different cost paradigms, namely query-wise and time-oriented measures of effort. Our multi-perspective evaluation scheme reveals new insights about query strategies, the impact of modalities, and different user types in simulated WTR search sessions., Comment: 4 pages + references; accepted at CIKM'23