Foundation models (e.g., CLIP or DINOv2) have shown their impressive learning and transfer capabilities in a wide range of visual tasks, by training on a large corpus of data and adapting to specific downstream tasks. It is, however, interesting that foundation models have not been fully explored for universal domain adaptation (UniDA), which is to learn models using labeled data in a source domain and unlabeled data in a target one, such that the learned models can successfully adapt to the target data. In this paper, we make comprehensive empirical studies of state-of-the-art UniDA methods using foundation models. We first observe that, unlike fine-tuning from ImageNet pre-trained models, as previous methods do, fine-tuning from foundation models yields significantly poorer results, sometimes even worse than training from scratch. While freezing the backbones, we demonstrate that although the foundation models greatly improve the performance of the baseline method that trains the models on the source data alone, existing UniDA methods generally fail to improve over the baseline. This suggests that new research efforts are very necessary for UniDA using foundation models. Based on these findings, we introduce \textit{CLIP distillation}, a parameter-free method specifically designed to distill target knowledge from CLIP models. The core of our \textit{CLIP distillation} lies in a self-calibration technique for automatic temperature scaling, a feature that significantly enhances the baseline's out-class detection capability. Although simple, our method outperforms previous approaches in most benchmark tasks, excelling in evaluation metrics including H-score/H$^3$-score and the newly proposed universal classification rate (UCR) metric. We hope that our investigation and the proposed simple framework can serve as a strong baseline to facilitate future studies in this field.

We present the task description of the Detection and Classification of Acoustic Scenes and Events (DCASE) 2023 Challenge Task 2: ``First-shot unsupervised anomalous sound detection (ASD) for machine condition monitoring''. The main goal is to enable rapid deployment of ASD systems for new kinds of machines without the need for hyperparameter tuning. In the past ASD tasks, developed methods tuned hyperparameters for each machine type, as the development and evaluation datasets had the same machine types. However, collecting normal and anomalous data as the development dataset can be infeasible in practice. In 2023 Task 2, we focus on solving the first-shot problem, which is the challenge of training a model on a completely novel machine type. Specifically, (i) each machine type has only one section (a subset of machine type) and (ii) machine types in the development and evaluation datasets are completely different. Analysis of 86 submissions from 23 teams revealed that the keys to outperform baselines were: 1) sampling techniques for dealing with class imbalances across different domains and attributes, 2) generation of synthetic samples for robust detection, and 3) use of multiple large pre-trained models to extract meaningful embeddings for the anomaly detector.

Selecting the right set of hyperparameters is crucial in time series forecasting. The classical temporal cross-validation framework for hyperparameter optimization (HPO) often leads to poor test performance because of a possible mismatch between validation and test periods. To address this test-validation mismatch, we propose a novel technique, H-Pro to drive HPO via test proxies by exploiting data hierarchies often associated with time series datasets. Since higher-level aggregated time series often show less irregularity and better predictability as compared to the lowest-level time series which can be sparse and intermittent, we optimize the hyperparameters of the lowest-level base-forecaster by leveraging the proxy forecasts for the test period generated from the forecasters at higher levels. H-Pro can be applied on any off-the-shelf machine learning model to perform HPO. We validate the efficacy of our technique with extensive empirical evaluation on five publicly available hierarchical forecasting datasets. Our approach outperforms existing state-of-the-art methods in Tourism, Wiki, and Traffic datasets, and achieves competitive result in Tourism-L dataset, without any model-specific enhancements. Moreover, our method outperforms the winning method of the M5 forecast accuracy competition.

We exploit field guides to learn bird species recognition, in particular zero-shot recognition of unseen species. Illustrations contained in field guides deliberately focus on discriminative properties of each species, and can serve as side information to transfer knowledge from seen to unseen bird species. We study two approaches: (1) a contrastive encoding of illustrations, which can be fed into standard zero-shot learning schemes; and (2) a novel method that leverages the fact that illustrations are also images and as such structurally more similar to photographs than other kinds of side information. Our results show that illustrations from field guides, which are readily available for a wide range of species, are indeed a competitive source of side information for zero-shot learning. On a subset of the iNaturalist2021 dataset with 749 seen and 739 unseen species, we obtain a classification accuracy of unseen bird species of $12\%$ @top-1 and $38\%$ @top-10, which shows the potential of field guides for challenging real-world scenarios with many species. Our code is available at https://github.com/ac-rodriguez/zsl_billow

We present a novel method for tuning the regularization hyper-parameter, $\lambda$, of a ridge regression that is faster to compute than leave-one-out cross-validation (LOOCV) while yielding estimates of the regression parameters of equal, or particularly in the setting of sparse covariates, superior quality to those obtained by minimising the LOOCV risk. The LOOCV risk can suffer from multiple and bad local minima for finite $n$ and thus requires the specification of a set of candidate $\lambda$, which can fail to provide good solutions. In contrast, we show that the proposed method is guaranteed to find a unique optimal solution for large enough $n$, under relatively mild conditions, without requiring the specification of any difficult to determine hyper-parameters. This is based on a Bayesian formulation of ridge regression that we prove to have a unimodal posterior for large enough $n$, allowing for both the optimal $\lambda$ and the regression coefficients to be jointly learned within an iterative expectation maximization (EM) procedure. Importantly, we show that by utilizing an appropriate preprocessing step, a single iteration of the main EM loop can be implemented in $O(\min(n, p))$ operations, for input data with $n$ rows and $p$ columns. In contrast, evaluating a single value of $\lambda$ using fast LOOCV costs $O(n \min(n, p))$ operations when using the same preprocessing. This advantage amounts to an asymptotic improvement of a factor of $l$ for $l$ candidate values for $\lambda$ (in the regime $q, p \in O(\sqrt{n})$ where $q$ is the number of regression targets).

Time series that record temporal changes in sets of system variables are ubiquitous across many scientific disciplines [1], from physics and engineering [2] to biomedicine [3, 4], climate science [5, 6], economics [7, 8] or online human behaviour [9, 10]. Many real-world systems are thus described as multivariate time series of (possibly) interlinked processes tracking the temporal evolution (deterministic or random) of groups of observables of interest. The relationships between the measured variables are often complex, in many cases displaying inter-dependencies among each other. For example, the spreading of Covid-19 in Indonesia was dependent on weather conditions [11]; the Sustainable Development Goals have extensive interlinkages [12]; there are strong interconnections between foreign exchange and cryptocurrencies [13]; and the brain displays multiple spatial and temporal scales of functional connectivity [14]. Driven by technological advances (e.g., imaging techniques in the brain sciences [15], or the increased connectivity of personal devices via the Internet of Things [16]), there is a rapid expansion in the collection and storage of multivariate time series data sets, which underlines the need for mathematical tools to analyze the interdependencies within complex high-dimensional time series data.

While deep learning models have seen widespread success in controlled environments, there are still barriers to their adoption in open-world settings. One critical task for safe deployment is the detection of anomalous or out-of-distribution samples that may require human intervention. In this work, we present a novel loss function and recipe for training networks with improved density-based out-of-distribution sensitivity. We demonstrate the effectiveness of our method on CIFAR-10, notably reducing the false-positive rate of the relative Mahalanobis distance method on far-OOD tasks by over 50%.

Implementing effective control mechanisms to ensure the proper functioning and security of deployed NLP models, from translation to chatbots, is essential. A key ingredient to ensure safe system behaviour is Out-Of-Distribution (OOD) detection, which aims to detect whether an input sample is statistically far from the training distribution. Although OOD detection is a widely covered topic in classification tasks, most methods rely on hidden features output by the encoder. In this work, we focus on leveraging soft-probabilities in a black-box framework, i.e. we can access the soft-predictions but not the internal states of the model. Our contributions include: (i) RAINPROOF a Relative informAItioN Projection OOD detection framework; and (ii) a more operational evaluation setting for OOD detection. Surprisingly, we find that OOD detection is not necessarily aligned with task-specific measures. The OOD detector may filter out samples well processed by the model and keep samples that are not, leading to weaker performance. Our results show that RAINPROOF provides OOD detection methods more aligned with task-specific performance metrics than traditional OOD detectors.

Electric vehicles (EVs) play an important role in reducing carbon emissions. As EV adoption accelerates, safety issues caused by EV batteries have become an important research topic. In order to benchmark and develop data-driven methods for this task, we introduce a large and comprehensive dataset of EV batteries. Our dataset includes charging records collected from hundreds of EVs from three manufacturers over several years. Our dataset is the first large-scale public dataset on real-world battery data, as existing data either include only several vehicles or is collected in the lab environment. Meanwhile, our dataset features two types of labels, corresponding to two key tasks - battery health estimation and battery capacity estimation. In addition to demonstrating how existing deep learning algorithms can be applied to this task, we further develop an algorithm that exploits the data structure of battery systems. Our algorithm achieves better results and shows that a customized method can improve model performances. We hope that this public dataset provides valuable resources for researchers, policymakers, and industry professionals to better understand the dynamics of EV battery aging and support the transition toward a sustainable transportation system.

We revisit the fundamental question of simple-versus-simple hypothesis testing with an eye towards computational complexity, as the statistically optimal likelihood ratio test is often computationally intractable in high-dimensional settings. In the classical spiked Wigner model (with a general i.i.d. spike prior) we show that an existing test based on linear spectral statistics achieves the best possible tradeoff curve between type I and type II error rates among all computationally efficient tests, even though there are exponential-time tests that do better. This result is conditional on an appropriate complexity-theoretic conjecture, namely a natural strengthening of the well-established low-degree conjecture. Our result shows that the spectrum is a sufficient statistic for computationally bounded tests (but not for all tests). To our knowledge, our approach gives the first tool for reasoning about the precise asymptotic testing error achievable with efficient computation. The main ingredients required for our hardness result are a sharp bound on the norm of the low-degree likelihood ratio along with (counterintuitively) a positive result on achievability of testing. This strategy appears to be new even in the setting of unbounded computation, in which case it gives an alternate way to analyze the fundamental statistical limits of testing.