Generalized Category Discovery (GCD) aims to classify labeled instances from known categories while discovering novel categories from unlabeled data. Despite recent progress in GCD for computer vision, existing GCD approaches largely rely on static final-step representations (in the visual domain), overlooking the temporally evolving nature of time-series data. In this paper, we introduce TGCD, the first framework specifically designed for GCD in time-series data. TGCD leverages both the dynamics of latent representations and the heterogeneity of predictions across multiple temporal segments to disover unknown (i.e., novel) categories, based on a pre-trained time-series foundation model. We propose a unified learning objective for TGCD that integrates the following three components: (i) a Stochastic Temporal Segment Dropout (STeSD) objective that regularizes the model by selectively penalizing high-entropy segments to encourage confident predictions on uncertain regions of the time-series, and (ii) a Known–Unknown Temporal Discriminability (KUTD) objective that promotes representational separation between known and unknown categories within unlabeled data and (iii) a margin-aware classification objective to improve generalization. Empirical evaluation on six multivariate time-series data sets demonstrates that the TGCD substantially outperforms existing GCD methods, particularly in discovering unknown categories. We further conduct ablation studies to highlight the individual contributions of each component. Additionally, we provide the first comprehensive benchmarking of recent GCD approaches on time-series data, revealing the limitations of naive transfer and underscoring the benefits of temporal modeling.

Deep learning models are increasingly used for making predictions based on clinical time-series data, but model generalization remains a challenge. Continual learning approaches, which preserve representations while learning new distributions, are suitable for addressing this challenge. We propose Continual Bayesian Long Short Term Memory (C-BLSTM), a continual learning algorithm based on the Bayesian LSTM model for domain incremental learning. C-BLSTM continually learns a sequence of tasks by combining architectural pruning, variational inference-based regularization, and coreset replay strategies. In extensive experiments on two public electronic medical record datasets for mortality prediction, we show that C-BLSTM outperforms many state-of-the-art continual learning approaches. Further, we apply the C-BLSTM to two real-world clinical time series datasets for prediction of readmission risk in patients with heart failure and glycated haemoglobin outcomes in patients with type 2 diabetes. First, we show that these datasets exhibit domain incremental characteristics with significant drifts in their marginal distributions and moderate drifts in their conditional distributions. Then, we demonstrate that the C-BLSTM improves generalization in five diverse real-world scenarios spanning temporal, site, device, case mix, and ethnicity shifts, both in terms of performance and reliability of predictions.

As vision-language models advance, addressing the Zero-Shot Learning (ZSL) problem in the open world becomes increasingly crucial. Specifically, a robust model must handle three types of samples during inference: seen classes with visual and semantic information provided in training, unseen classes with only the semantic information in training, and unknown samples with no prior information from training. Existing methods either handle seen and unseen classes together (ZSL) or seen and unknown classes (known as Open-Set Recognition, OSR). However, none addresses the simultaneous handling of all three, which we term Open-Set Zero-Shot Learning (OZSL). To address this problem, we propose a two-stage approach for OZSL that recognizes seen, unseen, and unknown samples. The first stage classifies samples as either seen or not, while the second stage distinguishes unseen from unknown. Furthermore, we introduce a cross-stage knowledge transfer mechanism that leverages semantic relationships between seen and unseen classes to enhance learning in the second stage. Extensive experiments demonstrate the efficacy of the proposed approach compared to naívely combining existing ZSL and OSR methods. The code is available at https://github.com/smufang/OZSL.

This paper tackles the out-of-distribution (OOD) detection problem for natural language classifiers. While the previous OOD detection methods require large-scale in-distribution (ID) training data, we attack this problem from the few-shot perspective in an unsupervised manner where the training relies on only a few samples from ID data. First, we develop various baselines for Few-shot OOD (FSOOD) detection in text classification based on the three well-known few-shot learning approaches (well-explored in the vision domain), i.e., meta-learning, metric learning, and data augmentation (DA). Then, we introduce the concept of demonstration-based data augmentation with meta and metric-learning approaches to reap the combined benefit of both approaches. A pre-trained transformer is fine-tuned on a few available ID samples in all developed methods. In tandem with this fine-tuning, an OOD detector is fitted over the ID training samples to reject the data from the unknown classes using two kinds of distance metrics, namely Mahalanobis distance and Cosine similarity. At last, we present an extensive evaluation of three ID datasets and three OOD datasets. We also perform an ablation study to analyze the impact of various components of our method.

Recently, many researchers have attempted to improve deep learning-based object detection models, both in terms of accuracy and operational speeds. However, frequently, there is a trade-off between speed and accuracy of such models, which encumbers their use in practical applications such as autonomous navigation. In this paper, we explore a meta-cognitive learning strategy for object detection to improve generalization ability while at the same time maintaining detection speed. The meta-cognitive method selectively samples the object instances in the training dataset to reduce overfitting. We use YOLO v3 Tiny as a base model for the work and evaluate the performance using the MS COCO dataset. The experimental results indicate an improvement in absolute precision of 2.6% (minimum), and 4.4% (maximum), with no overhead to inference time.

In the past few years, kernel-based one-class extreme learning machine (ELM) receives quite a lot of attention by researchers for offline/batch learning due to its noniterative and fast learning capability. This paper extends this concept for adaptive online learning with regularized kernel-based one-class ELM classifiers for detection of outliers, and are collectively referred to as ORK-OCELM. Two frameworks, viz., boundary and reconstruction, are presented to detect the target class in ORK-OCELM. The kernel hyperplane-based baseline one-class ELM model considers whole data in a single chunk, however, the proposed one-class classifiers are adapted in an online fashion from the stream of training samples. The performance of ORK-OCELM is evaluated on a standard benchmark as well as synthetic datasets for both types of environments, i.e., stationary and nonstationary. While evaluating on stationary datasets, these classifiers are compared against batch learning-based one-class classifiers. Similarly, while evaluating on nonstationary datasets, the comparison is done with incremental learning-based online one-class classifiers. The results indicate that the proposed classifiers yield better or similar outcomes for both. In the nonstationary dataset evaluation, adaptability of the proposed classifiers in a changing environment is also demonstrated. It is further shown that the proposed classifiers have large stream data handling capability even under limited system memory. Moreover, the proposed classifiers gain significant time improvement compared to traditional online one-class classifiers (in all aspects of training and testing). A faster learning ability of the proposed classifiers makes them more suitable for real-time anomaly detection.

Construction of multi-class classifiers using homogeneous combination of Extreme Learning Machine (ELM) based one-class classifiers have been proposed in this paper. Each class has been trained using individual one-class classifier and any new sample will belong to that class, which will yield maximum value. Proposed methods can be used to detect unknown outliers using multi-class classifiers. Two recently proposed one-class classifiers viz., kernel and random feature mapping based one-class ELM, is extended for multi-class construction in this paper. Further, we construct one-class classifier based multi-class classifier in two ways: with rejection and without rejection of few samples during training. We also perform consistency based model selection for optimal parameters selection in one-class classifier. We have tested the generalization capability of the proposed classifiers on 6 synthetic datasets and two benchmark datasets.