Related papers: How many classes do we need to see for novel class…

Causal discovery aims to learn causal relationships between variables from targeted data, making it a fundamental task in machine learning. However, causal discovery algorithms often rely on unverifiable causal assumptions, which are…

We present a new approach, called meta-meta classification, to learning in small-data settings. In this approach, one uses a large set of learning problems to design an ensemble of learners, where each learner has high bias and low variance…

Neural-network classifiers achieve high accuracy when predicting the class of an input that they were trained to identify. Maintaining this accuracy in dynamic environments, where inputs frequently fall outside the fixed set of initially…

This paper tackles the problem of novel category discovery (NCD), which aims to discriminate unknown categories in large-scale image collections. The NCD task is challenging due to the closeness to the real-world scenarios, where we have…

A learning classifier must outperform a trivial solution, in case of imbalanced data, this condition usually does not hold true. To overcome this problem, we propose a novel data level resampling method - Clustering Based Oversampling for…

The problem of data non-stationarity is commonly addressed in data stream processing. In a dynamic environment, methods should continuously be ready to analyze time-varying data -- hence, they should enable incremental training and respond…

In most works on deep incremental learning research, it is assumed that novel samples are pre-identified for neural network retraining. However, practical deep classifiers often misidentify these samples, leading to erroneous predictions.…

Facilitated by the powerful feature extraction ability of neural networks, deep clustering has achieved great success in analyzing high-dimensional and complex real-world data. The performance of deep clustering methods is affected by…

For open world applications, deep neural networks (DNNs) need to be aware of previously unseen data and adaptable to evolving environments. Furthermore, it is desirable to detect and learn novel classes which are not included in the DNNs…

Traditional machine learning excels on static benchmarks, but the real world is dynamic and seldom as carefully curated as test sets. Practical applications may generally encounter undesired inputs, are required to deal with novel…

Understanding causality helps to structure interventions to achieve specific goals and enables predictions under interventions. With the growing importance of learning causal relationships, causal discovery tasks have transitioned from…

Object detectors are typically trained once and for all on a fixed set of classes. However, this closed-world assumption is unrealistic in practice, as new classes will inevitably emerge after the detector is deployed in the wild. In this…

Active learning methods increase classification quality by means of user feedback. An important subcategory is active learning for outlier detection with one-class classifiers. While various methods in this category exist, selecting one for…

This paper introduces a novel, generic active learning method for one-class classification. Active learning methods play an important role to reduce the efforts of manual labeling in the field of machine learning. Although many active…

We argue that, when establishing and benchmarking Machine Learning (ML) models, the research community should favour evaluation metrics that better capture the value delivered by their model in practical applications. For a specific class…

Classification algorithms aim to predict an unknown label (e.g., a quality class) for a new instance (e.g., a product). Therefore, training samples (instances and labels) are used to deduct classification hypotheses. Often, it is relatively…

Deep models trained with noisy labels are prone to over-fitting and struggle in generalization. Most existing solutions are based on an ideal assumption that the label noise is class-conditional, i.e., instances of the same class share the…

This paper addresses the open set recognition (OSR) problem, where the goal is to correctly classify samples of known classes while detecting unknown samples to reject. In the OSR problem, "unknown" is assumed to have infinite possibilities…

In multi-label classification, each training instance is associated with multiple class labels simultaneously. Unfortunately, collecting the fully precise class labels for each training instance is time- and labor-consuming for real-world…

Novelty Detection methods identify samples that are not representative of a model's training set thereby flagging misleading predictions and bringing a greater flexibility and transparency at deployment time. However, research in this area…