Related papers: From Weak to Strong Sound Event Labels using Adapt…

We propose a general purpose active learning algorithm for structured prediction, gathering labeled data for training a model that outputs a set of related labels for an image or video. Active learning starts with a limited initial training…

Detecting anomalies in temporal data has gained significant attention across various real-world applications, aiming to identify unusual events and mitigate potential hazards. In practice, situations often involve a mix of segment-level…

Active learning, which effectively collects informative unlabeled data for annotation, reduces the demand for labeled data. In this work, we propose to retrieve unlabeled samples with a local sensitivity and hardness-aware acquisition…

The vast amounts of audio data collected in Sound Event Detection (SED) applications require efficient annotation strategies to enable supervised learning. Manual labeling is expensive and time-consuming, making Active Learning (AL) a…

Access to large corpora with strongly labelled sound events is expensive and difficult in engineering applications. Much research turns to address the problem of how to detect both the types and the timestamps of sound events with weak…

The objective of this work is to find temporal boundaries between signs in continuous sign language. Motivated by the paucity of annotation available for this task, we propose a simple yet effective algorithm to improve segmentation…

Active learning with strong and weak labelers considers a practical setting where we have access to both costly but accurate strong labelers and inaccurate but cheap predictions provided by weak labelers. We study this problem in the…

Audio tagging aims to predict one or several labels in an audio clip. Many previous works use weakly labelled data (WLD) for audio tagging, where only presence or absence of sound events is known, but the order of sound events is unknown.…

Deep neural networks have reached high accuracy on object detection but their success hinges on large amounts of labeled data. To reduce the labels dependency, various active learning strategies have been proposed, typically based on the…

To discover intrinsic inter-class transition probabilities underlying data, learning with noise transition has become an important approach for robust deep learning on corrupted labels. Prior methods attempt to achieve such transition…

Deep learning-based techniques have proven effective in polyp segmentation tasks when provided with sufficient pixel-wise labeled data. However, the high cost of manual annotation has created a bottleneck for model generalization. To…

Scribble-based weakly supervised semantic segmentation leverages only a few annotated pixels as labels to train a segmentation model, presenting significant potential for reducing the human labor involved in the annotation process. This…

Universal Multi-source Domain Adaptation (UniMDA) transfers knowledge from multiple labeled source domains to an unlabeled target domain under domain shifts (different data distribution) and class shifts (unknown target classes). Existing…

High-quality labels are often very scarce, whereas unlabeled data with inferred weak labels occurs more naturally. In many cases, these weak labels dictate the frequency of each respective class over a set of instances. In this paper, we…

CNN visualization and interpretation methods, like class-activation maps (CAMs), are typically used to highlight the image regions linked to class predictions. These models allow to simultaneously classify images and extract class-dependent…

Sound event detection (SED) methods typically rely on either strongly labelled data or weakly labelled data. As an alternative, sequentially labelled data (SLD) was proposed. In SLD, the events and the order of events in audio clips are…

Competitive point cloud semantic segmentation results usually rely on a large amount of labeled data. However, data annotation is a time-consuming and labor-intensive task, particularly for three-dimensional point cloud data. Thus,…

Label noise is emerging as a pressing issue in sound event classification. This arises as we move towards larger datasets that are difficult to annotate manually, but it is even more severe if datasets are collected automatically from…

The great success that deep models have achieved in the past is mainly owed to large amounts of labeled training data. However, the acquisition of labeled data for new tasks aside from existing benchmarks is both challenging and costly.…

Weakly labelled audio tagging aims to predict the classes of sound events within an audio clip, where the onset and offset times of the sound events are not provided. Previous works have used the multiple instance learning (MIL) framework,…