Related papers: Merlin L48 Spectrogram Dataset
Learning from noisy labels (LNL) is a challenge that arises in many real-world scenarios where collected training data can contain incorrect or corrupted labels. Most existing solutions identify noisy labels and adopt active learning to…
Deep learning with noisy labels is a challenging task. Recent prominent methods that build on a specific sample selection (SS) strategy and a specific semi-supervised learning (SSL) model achieved state-of-the-art performance. Intuitively,…
Most existing few-shot learning (FSL) methods require a large amount of labeled data in meta-training, which is a major limit. To reduce the requirement of labels, a semi-supervised meta-training (SSMT) setting has been proposed for FSL,…
In this paper we propose novel methodologies to construct Support Vector Machine -based classifiers that takes into account that label noises occur in the training sample. We propose different alternatives based on solving Mixed Integer…
NLP benchmarks rely on standardized datasets for training and evaluating models and are crucial for advancing the field. Traditionally, expert annotations ensure high-quality labels; however, the cost of expert annotation does not scale…
Speculative Decoding (SD) has emerged as a critical technique for accelerating Large Language Model (LLM) inference. Unlike deterministic system optimizations, SD performance is inherently data-dependent, meaning that diverse and…
While much of recent study in semi-supervised learning (SSL) has achieved strong performance on single-label classification problems, an equally important yet underexplored problem is how to leverage the advantage of unlabeled data in…
Due to the high human cost of annotation, it is non-trivial to curate a large-scale medical dataset that is fully labeled for all classes of interest. Instead, it would be convenient to collect multiple small partially labeled datasets from…
Audio classification has seen great progress with the increasing availability of large-scale datasets. These large datasets, however, are often only partially labeled as collecting full annotations is a tedious and expensive process. This…
Analyses for biodiversity monitoring based on passive acoustic monitoring (PAM) recordings is time-consuming and challenged by the presence of background noise in recordings. Existing models for sound event detection (SED) worked only on…
Large-scale datasets in the real world inevitably involve label noise. Deep models can gradually overfit noisy labels and thus degrade model generalization. To mitigate the effects of label noise, learning with noisy labels (LNL) methods…
Class imbalance is an inherent characteristic of multi-label data that hinders most multi-label learning methods. One efficient and flexible strategy to deal with this problem is to employ sampling techniques before training a multi-label…
The original ImageNet benchmark enforces a single-label assumption, despite many images depicting multiple objects. This leads to label noise and limits the richness of the learning signal. Multi-label annotations more accurately reflect…
It remains difficult to evaluate machine learning classifiers in the absence of a large, labeled dataset. While labeled data can be prohibitively expensive or impossible to obtain, unlabeled data is plentiful. Here, we introduce…
Supervised learning techniques are at the center of many tasks in remote sensing. Unfortunately, these methods, especially recent deep learning methods, often require large amounts of labeled data for training. Even though satellites…
In supervised machine learning, models are typically trained using data with hard labels, i.e., definite assignments of class membership. This traditional approach, however, does not take the inherent uncertainty in these labels into…
Music emotion recognition (MER) aims to identify the emotions conveyed in a given musical piece. However, currently, in the field of MER, the available public datasets have limited sample sizes. Recently, segment-based methods for…
Convolutional Dictionary Learning (CDL) has emerged as a powerful approach for signal representation by learning translation-invariant features through convolution operations. While existing CDL methods are predominantly designed and used…
The labor-intensive annotation process of semantic segmentation datasets is often prone to errors, since humans struggle to label every pixel correctly. We study algorithms to automatically detect such annotation errors, in particular…
Multi-annotator learning (MAL) aims to model annotator-specific labeling patterns. However, existing methods face a critical challenge: they simply skip updating annotator-specific model parameters when encountering missing labels, i.e., a…