Related papers: Merlin L48 Spectrogram Dataset
High-quality pixel-level annotations are essential for the semantic segmentation of remote sensing imagery. However, such labels are expensive to obtain and often affected by noise due to the labor-intensive and time-consuming nature of…
Data lies at the core of modern deep learning. The impressive performance of supervised learning is built upon a base of massive accurately labeled data. However, in some real-world applications, accurate labeling might not be viable;…
Audio-based equipment condition monitoring suffers from a lack of standardized methodologies for algorithm selection, hindering reproducible research. This paper addresses this gap by introducing a comprehensive framework for the systematic…
We introduce MarginMatch, a new SSL approach combining consistency regularization and pseudo-labeling, with its main novelty arising from the use of unlabeled data training dynamics to measure pseudo-label quality. Instead of using only the…
Semi-supervised learning (SSL) constructs classifiers from datasets in which only a subset of observations is labelled, a situation that naturally arises because obtaining labels often requires expert judgement or costly manual effort. This…
Learning with reduced labeling standards, such as noisy label, partial label, and multiple label candidates, which we generically refer to as \textit{imprecise} labels, is a commonplace challenge in machine learning tasks. Previous methods…
Collecting a large number of reliable training images annotated by multiple land-cover class labels in the framework of multi-label classification is time-consuming and costly in remote sensing (RS). To address this problem, publicly…
Current deep learning paradigms largely benefit from the tremendous amount of annotated data. However, the quality of the annotations often varies among labelers. Multi-observer studies have been conducted to study these annotation…
Performing controlled experiments on noisy data is essential in understanding deep learning across noise levels. Due to the lack of suitable datasets, previous research has only examined deep learning on controlled synthetic label noise,…
Multimodal emotion recognition is an important research topic in artificial intelligence. Over the past few decades, researchers have made remarkable progress by increasing the dataset size and building more effective algorithms. However,…
Large language models (LLMs) are being increasingly tuned to power complex generation tasks such as writing, fact-seeking, querying and reasoning. Traditionally, human or model feedback for evaluating and further tuning LLM performance has…
Deep learning models rely heavily on large volumes of labeled data to achieve high performance. However, real-world datasets often contain noisy labels due to human error, ambiguity, or resource constraints during the annotation process.…
Effective processing, interpretation, and management of sensor data have emerged as a critical component of cyber-physical systems. Traditionally, processing sensor data requires profound theoretical knowledge and proficiency in…
In this position paper, we argue that the classical evaluation on Natural Language Processing (NLP) tasks using annotated benchmarks is in trouble. The worst kind of data contamination happens when a Large Language Model (LLM) is trained on…
This work follows the approach of multi-label classification for non-intrusive load monitoring (NILM). We modify the popular sparse representation based classification (SRC) approach (developed for single label classification) to solve…
A significant challenge in sound event detection (SED) is the effective utilization of unlabeled data, given the limited availability of labeled data due to high annotation costs. Semi-supervised algorithms rely on labeled data to learn…
The precipitous rise and adoption of Large Language Models (LLMs) have shattered expectations with the fastest adoption rate of any consumer-facing technology in history. Healthcare, a field that traditionally uses NLP techniques, was bound…
Learning with noisy labels (LNL) aims to ensure model generalization given a label-corrupted training set. In this work, we investigate a rarely studied scenario of LNL on fine-grained datasets (LNL-FG), which is more practical and…
Self-supervised learning (SSL) methods targeting scene images have seen a rapid growth recently, and they mostly rely on either a dedicated dense matching mechanism or a costly unsupervised object discovery module. This paper shows that…
Neural networks trained on real-world datasets with long-tailed label distributions are biased towards frequent classes and perform poorly on infrequent classes. The imbalance in the ratio of positive and negative samples for each class…