Open-source benchmark datasets have been a critical component for advancing machine learning for robot perception in terrestrial applications. Benchmark datasets enable the widespread development of state-of-the-art machine learning methods, which require large datasets for training, validation, and thorough comparison to competing approaches. Underwater environments impose several operational challenges that hinder efforts to collect large benchmark datasets for marine robot perception. Furthermore, a low abundance of targets of interest relative to the size of the search space leads to increased time and cost required to collect useful datasets for a specific task. As a result, there is limited availability of labeled benchmark datasets for underwater applications. We present the AI4Shipwrecks dataset, which consists of 24 distinct shipwreck sites totaling 286 high-resolution labeled side scan sonar images to advance the state-of-the-art in autonomous sonar image understanding. We leverage the unique abundance of targets in Thunder Bay National Marine Sanctuary in Lake Huron, MI, to collect and compile a sonar imagery benchmark dataset through surveys with an autonomous underwater vehicle (AUV). We consulted with expert marine archaeologists for the labeling of robotically gathered data. We then leverage this dataset to perform benchmark experiments for comparison of state-of-the-art supervised segmentation methods, and we present insights on opportunities and open challenges for the field. The dataset and benchmarking tools will be released as an open-source benchmark dataset to spur innovation in machine learning for Great Lakes and ocean exploration. The dataset and accompanying software are available at https://umfieldrobotics.github.io/ai4shipwrecks/.

This simulation study evaluates the effectiveness of multiple imputation (MI) techniques for multilevel data. It compares the performance of traditional Multiple Imputation by Chained Equations (MICE) with tree-based methods such as Chained Random Forests with Predictive Mean Matching and Extreme Gradient Boosting. Adapted versions that include dummy variables for cluster membership are also included for the tree-based methods. Methods are evaluated for coefficient estimation bias, statistical power, and type I error rates on simulated hierarchical data with different cluster sizes (25 and 50) and levels of missingness (10\% and 50\%). Coefficients are estimated using random intercept and random slope models. The results show that while MICE is preferred for accurate rejection rates, Extreme Gradient Boosting is advantageous for reducing bias. Furthermore, the study finds that bias levels are similar across different cluster sizes, but rejection rates tend to be less favorable with fewer clusters (lower power, higher type I error). In addition, the inclusion of cluster dummies in tree-based methods improves estimation for Level 1 variables, but is less effective for Level 2 variables. When data become too complex and MICE is too slow, extreme gradient boosting is a good alternative for hierarchical data. Keywords: Multiple imputation; multi-level data; MICE; missRanger; mixgb

The standard evaluation protocol for measuring the quality of Knowledge Graph Completion methods - the task of inferring new links to be added to a graph - typically involves a step which ranks every entity of a Knowledge Graph to assess their fit as a head or tail of a candidate link to be added. In Knowledge Graphs on a larger scale, this task rapidly becomes prohibitively heavy. Previous approaches mitigate this problem by using random sampling of entities to assess the quality of links predicted or suggested by a method. However, we show that this approach has serious limitations since the ranking metrics produced do not properly reflect true outcomes. In this paper, we present a thorough analysis of these effects along with the following findings. First, we empirically find and theoretically motivate why sampling uniformly at random vastly overestimates the ranking performance of a method. We show that this can be attributed to the effect of easy versus hard negative candidates. Second, we propose a framework that uses relational recommenders to guide the selection of candidates for evaluation. We provide both theoretical and empirical justification of our methodology, and find that simple and fast methods can work extremely well, and that they match advanced neural approaches. Even when a large portion of true candidates for a property are missed, the estimation barely deteriorates. With our proposed framework, we can reduce the time and computation needed similar to random sampling strategies while vastly improving the estimation; on ogbl-wikikg2, we show that accurate estimations of the full, filtered ranking can be obtained in 20 seconds instead of 30 minutes. We conclude that considerable computational effort can be saved by effective preprocessing and sampling methods and still reliably predict performance accurately of the true performance for the entire ranking procedure.

Purpose: Limited studies exploring concrete methods or approaches to tackle and enhance model fairness in the radiology domain. Our proposed AI model utilizes supervised contrastive learning to minimize bias in CXR diagnosis. Materials and Methods: In this retrospective study, we evaluated our proposed method on two datasets: the Medical Imaging and Data Resource Center (MIDRC) dataset with 77,887 CXR images from 27,796 patients collected as of April 20, 2023 for COVID-19 diagnosis, and the NIH Chest X-ray (NIH-CXR) dataset with 112,120 CXR images from 30,805 patients collected between 1992 and 2015. In the NIH-CXR dataset, thoracic abnormalities include atelectasis, cardiomegaly, effusion, infiltration, mass, nodule, pneumonia, pneumothorax, consolidation, edema, emphysema, fibrosis, pleural thickening, or hernia. Our proposed method utilizes supervised contrastive learning with carefully selected positive and negative samples to generate fair image embeddings, which are fine-tuned for subsequent tasks to reduce bias in chest X-ray (CXR) diagnosis. We evaluated the methods using the marginal AUC difference ($\delta$ mAUC). Results: The proposed model showed a significant decrease in bias across all subgroups when compared to the baseline models, as evidenced by a paired T-test (p<0.0001). The $\delta$ mAUC obtained by our method were 0.0116 (95\% CI, 0.0110-0.0123), 0.2102 (95% CI, 0.2087-0.2118), and 0.1000 (95\% CI, 0.0988-0.1011) for sex, race, and age on MIDRC, and 0.0090 (95\% CI, 0.0082-0.0097) for sex and 0.0512 (95% CI, 0.0512-0.0532) for age on NIH-CXR, respectively. Conclusion: Employing supervised contrastive learning can mitigate bias in CXR diagnosis, addressing concerns of fairness and reliability in deep learning-based diagnostic methods.

Maritime transport is a pivotal logistics mode for the long-distance and bulk transportation of goods. However, the intricate planning involved in this mode is often hindered by uncertainties, including weather conditions, cargo diversity, and port dynamics, leading to increased costs. Consequently, accurately estimating vessel total (stay) time at port and potential delays becomes imperative for effective planning and scheduling in port operations. This study aims to develop a port operation solution with competitive prediction and classification capabilities for estimating vessel Total and Delay times. This research addresses a significant gap in port analysis models for vessel Stay and Delay times, offering a valuable contribution to the field of maritime logistics. The proposed solution is designed to assist decision-making in port environments and predict service delays. This is demonstrated through a case study on Brazil ports. Additionally, feature analysis is used to understand the key factors impacting maritime logistics, enhancing the overall understanding of the complexities involved in port operations.

Clouds play a significant role in global temperature regulation through their effect on planetary albedo. Anthropogenic emissions of aerosols can alter the albedo of clouds, but the extent of this effect, and its consequent impact on temperature change, remains uncertain. Human-induced clouds caused by ship aerosol emissions, commonly referred to as ship tracks, provide visible manifestations of this effect distinct from adjacent cloud regions and therefore serve as a useful sandbox to study human-induced clouds. However, the lack of large-scale ship track data makes it difficult to deduce their general effects on cloud formation. Towards developing automated approaches to localize ship tracks at scale, we present CloudTracks, a dataset containing 3,560 satellite images labeled with more than 12,000 ship track instance annotations. We train semantic segmentation and instance segmentation model baselines on our dataset and find that our best model substantially outperforms previous state-of-the-art for ship track localization (61.29 vs. 48.65 IoU). We also find that the best instance segmentation model is able to identify the number of ship tracks in each image more accurately than the previous state-of-the-art (1.64 vs. 4.99 MAE). However, we identify cases where the best model struggles to accurately localize and count ship tracks, so we believe CloudTracks will stimulate novel machine learning approaches to better detect elongated and overlapping features in satellite images. We release our dataset openly at {zenodo.org/records/10042922}.

The most popular classification algorithms are designed to maximize classification accuracy during training. However, this strategy may fail in the presence of class imbalance since it is possible to train models with high accuracy by overfitting to the majority class. On the other hand, the Area Under the Curve (AUC) is a widely used metric to compare classification performance of different algorithms when there is a class imbalance, and various approaches focusing on the direct optimization of this metric during training have been proposed. Among them, SVM-based formulations are especially popular as this formulation allows incorporating different regularization strategies easily. In this work, we develop a prototype learning approach that relies on cutting-plane method, similar to Ranking SVM, to maximize AUC. Our algorithm learns simpler models by iteratively introducing cutting planes, thus overfitting is prevented in an unconventional way. Furthermore, it penalizes the changes in the weights at each iteration to avoid large jumps that might be observed in the test performance, thus facilitating a smooth learning process. Based on the experiments conducted on 73 binary classification datasets, our method yields the best test AUC in 25 datasets among its relevant competitors.

Modern classification problems exhibit heterogeneities across individual classes: Each class may have unique attributes, such as sample size, label quality, or predictability (easy vs difficult), and variable importance at test-time. Without care, these heterogeneities impede the learning process, most notably, when optimizing fairness objectives. Confirming this, under a gaussian mixture setting, we show that the optimal SVM classifier for balanced accuracy needs to be adaptive to the class attributes. This motivates us to propose CAP: An effective and general method that generates a class-specific learning strategy (e.g. hyperparameter) based on the attributes of that class. This way, optimization process better adapts to heterogeneities. CAP leads to substantial improvements over the naive approach of assigning separate hyperparameters to each class. We instantiate CAP for loss function design and post-hoc logit adjustment, with emphasis on label-imbalanced problems. We show that CAP is competitive with prior art and its flexibility unlocks clear benefits for fairness objectives beyond balanced accuracy. Finally, we evaluate CAP on problems with label noise as well as weighted test objectives to showcase how CAP can jointly adapt to different heterogeneities.

In today's data-driven world, the proliferation of publicly available information intensifies the challenge of information leakage (IL), raising security concerns. IL involves unintentionally exposing secret (sensitive) information to unauthorized parties via systems' observable information. Conventional statistical approaches, which estimate mutual information (MI) between observable and secret information for detecting IL, face challenges such as the curse of dimensionality, convergence, computational complexity, and MI misestimation. Furthermore, emerging supervised machine learning (ML) methods, though effective, are limited to binary system-sensitive information and lack a comprehensive theoretical framework. To address these limitations, we establish a theoretical framework using statistical learning theory and information theory to accurately quantify and detect IL. We demonstrate that MI can be accurately estimated by approximating the log-loss and accuracy of the Bayes predictor. As the Bayes predictor is typically unknown in practice, we propose to approximate it with the help of automated machine learning (AutoML). First, we compare our MI estimation approaches against current baselines, using synthetic data sets generated using the multivariate normal (MVN) distribution with known MI. Second, we introduce a cut-off technique using one-sided statistical tests to detect IL, employing the Holm-Bonferroni correction to increase confidence in detection decisions. Our study evaluates IL detection performance on real-world data sets, highlighting the effectiveness of the Bayes predictor's log-loss estimation, and finds our proposed method to effectively estimate MI on synthetic data sets and thus detect ILs accurately.

Modern plankton high-throughput monitoring relies on deep learning classifiers for species recognition in water ecosystems. Despite satisfactory nominal performances, a significant challenge arises from Dataset Shift, which causes performances to drop during deployment. In our study, we integrate the ZooLake dataset with manually-annotated images from 10 independent days of deployment, serving as test cells to benchmark Out-Of-Dataset (OOD) performances. Our analysis reveals instances where classifiers, initially performing well in In-Dataset conditions, encounter notable failures in practical scenarios. For example, a MobileNet with a 92% nominal test accuracy shows a 77% OOD accuracy. We systematically investigate conditions leading to OOD performance drops and propose a preemptive assessment method to identify potential pitfalls when classifying new data, and pinpoint features in OOD images that adversely impact classification. We present a three-step pipeline: (i) identifying OOD degradation compared to nominal test performance, (ii) conducting a diagnostic analysis of degradation causes, and (iii) providing solutions. We find that ensembles of BEiT vision transformers, with targeted augmentations addressing OOD robustness, geometric ensembling, and rotation-based test-time augmentation, constitute the most robust model, which we call BEsT model. It achieves an 83% OOD accuracy, with errors concentrated on container classes. Moreover, it exhibits lower sensitivity to dataset shift, and reproduces well the plankton abundances. Our proposed pipeline is applicable to generic plankton classifiers, contingent on the availability of suitable test cells. By identifying critical shortcomings and offering practical procedures to fortify models against dataset shift, our study contributes to the development of more reliable plankton classification technologies.