Related papers: SIMILAR: Submodular Information Measures Based Act…

In this paper, we propose a novel semi-supervised learning (SSL) framework named BoostMIS that combines adaptive pseudo labeling and informative active annotation to unleash the potential of medical image SSL models: (1) BoostMIS can…

Non-intrusive load monitoring (NILM) focuses on disaggregating total household power consumption into appliance-specific usage. Many advanced NILM methods are based on neural networks that typically require substantial amounts of labeled…

Despite the recent success of Multimodal Foundation Models (FMs), their reliance on massive paired datasets limits their applicability in low-data and rare-scenario settings where aligned data is scarce and expensive. A key bottleneck is…

Temporal action proposals are a common module in action detection pipelines today. Most current methods for training action proposal modules rely on fully supervised approaches that require large amounts of annotated temporal action…

Active learning is a label-efficient approach to train highly effective models while interactively selecting only small subsets of unlabelled data for labelling and training. In "open world" settings, the classes of interest can make up a…

LiDAR-based semantic segmentation plays a vital role in autonomous driving by enabling detailed understanding of 3D environments. However, annotating LiDAR point clouds is extremely costly and requires assigning semantic labels to millions…

Deep neural networks usually require large labeled datasets for training to achieve state-of-the-art performance in many tasks, such as image classification and natural language processing. Although a lot of data is created each day by…

The aim in imitation learning is to learn effective policies by utilizing near-optimal expert demonstrations. However, high-quality demonstrations from human experts can be expensive to obtain in large numbers. On the other hand, it is…

Training deep object detectors demands expensive bounding box annotation. Active learning (AL) is a promising technique to alleviate the annotation burden. Performing AL at box-level for object detection, i.e., selecting the most…

Active Learning (AL) is a well-known standard method for efficiently obtaining annotated data by first labeling the samples that contain the most information based on a query strategy. In the past, a large variety of such query strategies…

Active learning (AL), which aims to construct an effective training set by iteratively curating the most formative unlabeled data for annotation, has been widely used in low-resource tasks. Most active learning techniques in classification…

Semi-Supervised Learning (SSL) can leverage abundant unlabeled data to boost model performance. However, the class-imbalanced data distribution in real-world scenarios poses great challenges to SSL, resulting in performance degradation.…

Deep neural networks perform remarkably well in close-world scenarios. However, novel classes emerged continually in real applications, making it necessary to learn incrementally. Class-incremental learning (CIL) aims to gradually recognize…

The promise of active learning (AL) is to reduce labelling costs by selecting the most valuable examples to annotate from a pool of unlabelled data. Identifying these examples is especially challenging with high-dimensional data (e.g.…

Recent studies highlight that deep learning models often learn spurious features mistakenly linked to labels, compromising their reliability in real-world scenarios where such correlations do not hold. Despite the increasing research…

An active learner is given a class of models, a large set of unlabeled examples, and the ability to interactively query labels of a subset of these examples; the goal of the learner is to learn a model in the class that fits the data well.…

State-of-the-art machine learning models require access to significant amount of annotated data in order to achieve the desired level of performance. While unlabelled data can be largely available and even abundant, annotation process can…

Active learning (AL) aims to optimize model training and reduce annotation costs by selecting the most informative samples for labeling. Typically, AL methods rely on the empirical distribution of labeled data to define the decision…

Recent semi-supervised learning methods have shown to achieve comparable results to their supervised counterparts while using only a small portion of labels in image classification tasks thanks to their regularization strategies. In this…

AI deployed in many real-world use cases should be capable of adapting to novelties encountered after deployment. Here, we consider a challenging, under-explored and realistic continual adaptation problem: a deployed AI agent is…