Source-free domain adaptation (SFDA) adapts a pre-trained model from a labeled source domain to an unlabeled target domain without source data access, preserving privacy. While SFDA is common in computer vision, it remains largely unexplored in time series analysis, where existing methods struggle to capture temporal dynamics and often produce overconfident predictions on out-of-distribution samples. We propose MAsk And imPUte (MAPU), which tackles temporal consistency through a novel imputation task, where randomly masked time series signals are recovered within the learned embedding space. During adaptation, a dedicated temporal imputer guides the target model to generate features that maintain temporal consistency with source features. However, MAPU relies on standard softmax predictions, leading to overconfident predictions on target samples that fall outside the source domain's support. To address this limitation, we introduce Evidential-MAPU (E-MAPU), which leverages evidential uncertainty estimation to identify these out-of-support samples and adapts the feature extractor to map them closer to the source domain's support, while maintaining the classifier fixed. Extensive experiments on five real-world time series datasets demonstrate significant performance improvements over existing methods. Our approaches effectively handle various time series domain adaptation challenges while maintaining computational efficiency, achieving state-of-the-art performance through its uncertainty-aware adaptation strategy.

Deep learning models achieve remarkable accuracy in computer vision tasks yet remain vulnerable to adversarial examples-carefully crafted perturbations to input images that can deceive these models into making confident but incorrect predictions. This vulnerability poses significant risks in high-stakes applications such as autonomous vehicles, security surveillance, and safety-critical inspection systems. While the existing literature extensively covers adversarial attacks in image classification, comprehensive analyses of such attacks on object detection systems remain limited. This article presents a novel taxonomic framework for categorizing adversarial attacks specific to object detection architectures, synthesizes existing robustness metrics, and provides a comprehensive empirical evaluation of state-of-the-art attack methodologies on popular object detection models, including both traditional detectors and modern detectors with vision-language pretraining. Through rigorous analysis of open-source attack implementations and their effectiveness across diverse detection architectures, we derive key insights into attack characteristics. Furthermore, we delineate critical research gaps and emerging challenges to guide future investigations in securing object detection systems against adversarial threats. Our findings establish a foundation for developing more robust detection models while highlighting the urgent need for standardized evaluation protocols in this rapidly evolving domain.

Domain adaptation is a critical task in machine learning that aims to improve model performance on a target domain by leveraging knowledge from a related source domain. In this work, we introduce Universal Semi-Supervised Do-main Adaptation (UniSSDA), a practical yet challenging setting where the target domain is partially labeled, and the source and target label space may not strictly match. UniSSDA is at the intersection of Universal Domain Adap-tation (UniDA) and Semi-Supervised Domain Adaptation (SSDA): the UniDA setting does not allow for fine-grained categorization of target private classes not represented in the source domain, while SSDA focuses on the restricted closed-set setting where source and target label spaces match exactly. Existing UniDA and SSDA methods are sus-ceptible to common-class bias in UniSSDA settings, where models overfit to data distributions of classes common to both domains at the expense of private classes. We pro-pose a new prior-guided pseudo-label refinement strategy to reduce the reinforcement of common-class bias due to pseudo-labeling, a common label propagation strategy in domain adaptation. We demonstrate the effectiveness of the proposed strategy on benchmark datasets Office-Home, Do-mainNet, and VisDA. The proposed strategy attains the best performance across UniSSDA adaptation settings and es-tablishes a new baseline for UniSSDA.

Source-free domain adaptation (SFDA) aims to adapt a source model trained on a fully-labeled source domain to an unlabeled target domain. Large-data pre-trained networks are used to initialize source models during source training, and subsequently discarded. However, source training can cause the model to overfit to source data distribution and lose applicable target domain knowledge. We propose to integrate the pre-trained network into the target adaptation process as it has diversified features important for generalization and provides an alternate view of features and classification decisions different from the source model. We propose to distil useful target domain information through a co-learning strategy to improve target pseudolabel quality for finetuning the source model. Evaluation on 4 benchmark datasets show that our proposed strategy improves adaptation performance and can be successfully integrated with existing SFDA methods. Leveraging modern pre-trained networks that have stronger representation learning ability in the co-learning strategy further boosts performance.

Domain generalization methods aim to learn models robust to domain shift with data from a limited number of source domains and without access to target domain samples during training. Popular domain alignment methods for domain generalization seek to extract domain-invariant features by minimizing the discrepancy between feature distributions across all domains, disregarding inter-domain relationships. In this paper, we instead propose a novel representation learning methodology that selectively enforces prediction consistency between source domains estimated to be closely-related. Specifically, we hypothesize that domains share different class-informative representations, so instead of aligning all domains which can cause negative transfer, we only regularize the discrepancy between closely-related domains. We apply our method to time-series classification tasks and conduct comprehensive experiments on three public real-world datasets. Our method significantly improves over the baseline and achieves better or competitive performance in comparison with state-of-the-art methods in terms of both accuracy and model calibration.

Deep networks are prone to performance degradation when there is a domain shift between the source (training) data and target (test) data. Recent test-time adaptation methods update batch normalization layers of pre-trained source models deployed in new target environments with streaming data. Although these methods can adapt on-the-fly without first collecting a large target domain dataset, their performance is dependent on streaming conditions such as mini-batch size and class-distribution which can be unpredictable in practice. In this work, we propose a framework for few-shot domain adaptation to address the practical challenges of data-efficient adaptation. Specifically, we propose a constrained optimization of feature normalization statistics in pre-trained source models supervised by a small target domain support set. Our method is easy to implement and improves source model performance with as little as one sample per class for classification tasks. Extensive experiments on 5 cross-domain classification and 4 semantic segmentation datasets show that our proposed method achieves more accurate and reliable performance than test-time adaptation, while not being constrained by streaming conditions.

Several techniques for multivariate time series anomaly detection have been proposed recently, but a systematic comparison on a common set of datasets and metrics is lacking. This article presents a systematic and comprehensive evaluation of unsupervised and semisupervised deep-learning-based methods for anomaly detection and diagnosis on multivariate time series data from cyberphysical systems. Unlike previous works, we vary themodeland post-processing of model errors, i.e., thescoring functionsindependently of each other, through a grid of ten models and four scoring functions, comparing these variants to state-of-the-art methods. In time-series anomaly detection, detecting anomalous events is more important than detecting individual anomalous time points. Through experiments, we find that the existing evaluation metrics either do not take events into account or cannot distinguish between a good detector and trivial detectors, such as a random or an all-positive detector. We propose a new metric to overcome these drawbacks, namely, the composite F-score (Fc1), for evaluating time-series anomaly detection. Our study highlights that dynamic scoring functions work much better than static ones for multivariate time series anomaly detection, and the choice of scoring functions often matters more than the choice of the underlying model. We also find that a simple, channel-wise model—the univariate fully connected auto-encoder, with the dynamic Gaussian scoring function emerges as a winning candidate for both anomaly detection and diagnosis, beating state-of-the-art algorithms.

While deep neural networks demonstrate state-of-the-art performance on a variety of learning tasks, their performance relies on the assumption that train and test distributions are the same, which may not hold in real-world applications. Domain generalization addresses this issue by employing multiple source domains to build robust models that can generalize to unseen target domains subject to shifts in data distribution. In this paper, we propose DomainFree Domain Generalization (DFDG), a model-agnostic method to achieve better generalization performance on the unseen test domain without the need for source domain labels. DFDG uses novel strategies to learn domain-invariant class-discriminative features. It aligns class relationships of samples through class-conditional soft labels, and uses saliency maps, traditionally developed for post-hoc analysis of image classification networks, to remove superficial observations from training inputs. DFDG obtains competitive performance on both time series sensor and image classification public datasets.

Online prediction for streaming time series data has practical use for many real-world applications where downstream decisions depend on accurate forecasts for the future. Deployment in dynamic environments requires models to adapt quickly to changing data distributions without overfitting. We propose POLA (Predicting Online by Learning rate Adaptation) to automatically regulate the learning rate of recurrent neural network models to adapt to changing time series patterns across time. POLA meta-learns the learning rate of the stochastic gradient descent (SGD) algorithm by assimilating the prequential or interleaved-test-then-train evaluation scheme for online prediction. We evaluate POLA on two real-world datasets across three commonly-used recurrent neural network models. POLA demonstrates overall comparable or better predictive performance over other online prediction methods.

Deep neural networks achieve state-of-the-art performance in a variety of tasks by extracting a rich set of features from unstructured data, however this performance is closely tied to model size. Modern techniques for inducing sparsity and reducing model size are (1) network pruning, (2) training with a sparsity inducing penalty, and (3) training a binary mask jointly with the weights of the network. We study different sparsity inducing penalties from the perspective of Bayesian hierarchical models and present a novel penalty called Hierarchical Adaptive Lasso (HALO) which learns to adaptively sparsify weights of a given network via trainable parameters. When used to train over-parametrized networks, our penalty yields small subnetworks with high accuracy without fine-tuning. Empirically, on image recognition tasks, we find that HALO is able to learn highly sparse network (only 5% of the parameters) with significant gains in performance over state-of-the-art magnitude pruning methods at the same level of sparsity. Code is available at https://github.com/skyler120/sparsity-halo.

Modeling and detection of seasonality in time series is essential for accurate analysis, prediction and anomaly detection. Examples of seasonal effects at different scales abound: the increase in consumer product sales during the holiday season recurs yearly, and similarly household electricity usage has daily, weekly and yearly cycles. The period in real-world time series, however, may be obfuscated by noise and missing values arising in data acquisition. How can one learn the natural periodicity from incomplete multivariate time series? We propose a robust framework for multivariate period detection, called LAPIS. It encodes incomplete and noisy data as a sparse summary via a Ramanujan periodic dictionary. LAPIS can accurately detect a mixture of multiple periods in the same time series even when 70% of the observations are missing. A key innovation of our framework is that it exploits shared periods across individual time series even when they are not correlated or in-phase. Beyond detecting periods, LAPIS enables improvements in downstream applications such as forecasting, missing value imputation and clustering. At the same time our approach scales to large real-world data executing within seconds on datasets of length up to half a million time points.

Learning accurate models of the physical world is required for a lot of robotic manipulation tasks. However, during manipulation, robots are expected to interact with un-known workpieces so that building predictive models which can generalize over a number of these objects is highly desirable. In this paper, we study the problem of designing deep learning agents which can generalize their models of the physical world by building context-aware learning models. The purpose of these agents is to quickly adapt and/or generalize their notion of physics of interaction in the real world based on certain features about the interacting objects that provide different contexts to the predictive models. With this motivation, we present context-aware zero shot learning (CAZSL, pronounced as casual) models, an approach utilizing a Siamese network architecture, embedding space masking and regularization based on context variables which allows us to learn a model that can generalize to different parameters or features of the interacting objects. We test our proposed learning algorithm on the recently released Omnipush datatset that allows testing of meta-learning capabilities using low-dimensional data. Codes for CAZSL are available at https://www.merl.com/research/license/CAZSL.

Change detection involves segmenting sequential data such that observations in the same segment share some desired properties. Multivariate change detection continues to be a challenging problem due to the variety of ways change points can be correlated across channels and the potentially poor signal-to-noise ratio on individual channels. In this paper, we are interested in locating additive outliers (AO) and level shifts (LS) in the unsupervised setting. We propose ABACUS, Automatic BAyesian Changepoints Under Sparsity, a Bayesian source separation technique to recover latent signals while also detecting changes in model parameters. Multi-level sparsity achieves both dimension reduction and modeling of signal changes. We show ABACUS has competitive or superior performance in simulation studies against state-of-the-art change detection methods and established latent variable models. We also illustrate ABACUS on two real application, modeling genomic profiles and analyzing household electricity consumption.

Heterogeneous sensor data fusion is a challenging field that has gathered significant interest in recent years. In this paper, we propose a neural network-based multimodal data fusion framework named deep multimodal encoder (DME). Through our new objective function, both the intra- and inter-modal correlations of multimodal sensor data can be better exploited for recovering the missing values, and the shared representation learned can be used directly for prediction tasks. In experiments with real-world sensor data, DME shows remarkable ability for missing data imputation and new modality prediction. Compared with traditional algorithms such as kNN and Sparse-PCA, DME is more expressive, robust, and scalable to large datasets.

The dynamic and unpredictable nature of energy harvesting sources that are used in wireless sensor networks necessitates the need for adaptive duty cycling techniques. Such adaptive control allows sensor nodes to achieve energy-neutrality, whereby both energy supply and demand are balanced. This paper proposes a framework enabling an adaptive duty cycling scheme for sensor networks that takes into account the operating duty cycle of the node, and application-level QoS requirements. We model the system as a Continuous Time Markov Chain (CTMC), and derive analytical expressions for key QoS metrics - such as latency, loss probability and power consumption. We then formulate and solve the optimal operating duty cycle as a non-linear optimization problem, using latency and loss probability as the constraints. Simulation results show that a Markovian duty cycling scheme can outperform periodic duty cycling schemes.