18 citations · 36 across the 16 of their papers we have counts for
19 papers
ALINC: Active Learning for Inductive Node Classification via Graph Sampling
Pascal Plettenberg, Denis Huseljic, André Alcalde +2
Active learning (AL) for node classification typically focuses on selecting the most informative nodes for annotation within one or a few large graphs (e.g., in social network anal…
BoSS: A Best-of-Strategies Selector as an Oracle for Deep Active Learning
Denis Huseljic, Paul Hahn, Marek Herde +2
Active learning (AL) aims to reduce annotation costs while maximizing model performance by iteratively selecting valuable instances. While foundation models have made it easier to…
Cleaning the Pool: Progressive Filtering of Unlabeled Pools in Deep Active Learning
Denis Huseljic, Marek Herde, Lukas Rauch +2
Existing active learning (AL) strategies capture fundamentally different notions of data value, e.g., uncertainty or representativeness. Consequently, the effectiveness of strategi…
No Free Lunch in Active Learning: LLM Embedding Quality Dictates Query Strategy Success
Lukas Rauch, Moritz Wirth, Denis Huseljic +3
The advent of large language models (LLMs) capable of producing general-purpose representations lets us revisit the practicality of deep active learning (AL): By leveraging frozen…
crowd-hpo: Realistic Hyperparameter Optimization and Benchmarking for Learning from Crowds with Noisy Labels
Marek Herde, Lukas Lührs, Denis Huseljic +1
Crowdworking is a cost-efficient solution for acquiring class labels. Since these labels are subject to noise, various approaches to learning from crowds have been proposed. Typica…
dopanim: A Dataset of Doppelganger Animals with Noisy Annotations from Multiple Humans
Marek Herde, Denis Huseljic, Lukas Rauch +1
Human annotators typically provide annotated data for training machine learning models, such as neural networks. Yet, human annotations are subject to noise, impairing generalizati…
Towards Deep Active Learning in Avian Bioacoustics
Lukas Rauch, Denis Huseljic, Moritz Wirth +3
Passive acoustic monitoring (PAM) in avian bioacoustics enables cost-effective and extensive data collection with minimal disruption to natural habitats. Despite advancements in co…
Annot-Mix: Learning with Noisy Class Labels from Multiple Annotators via a Mixup Extension
Marek Herde, Lukas Lührs, Denis Huseljic +1
Training with noisy class labels impairs neural networks' generalization performance. In this context, mixup is a popular regularization technique to improve training robustness by…
Fast Fishing: Approximating BAIT for Efficient and Scalable Deep Active Image Classification
Denis Huseljic, Paul Hahn, Marek Herde +2
Deep active learning (AL) seeks to minimize the annotation costs for training deep neural networks. BAIT, a recently proposed AL strategy based on the Fisher Information, has demon…
BirdSet: A Large-Scale Dataset for Audio Classification in Avian Bioacoustics
Lukas Rauch, Raphael Schwinger, Moritz Wirth +8
Deep learning (DL) has greatly advanced audio classification, yet the field is limited by the scarcity of large-scale benchmark datasets that have propelled progress in other domai…
Active Label Refinement for Semantic Segmentation of Satellite Images
Tuan Pham Minh, Jayan Wijesingha, Daniel Kottke +5
Remote sensing through semantic segmentation of satellite images contributes to the understanding and utilisation of the earth's surface. For this purpose, semantic segmentation ne…
ActiveGLAE: A Benchmark for Deep Active Learning with Transformers
Lukas Rauch, Matthias Aßenmacher, Denis Huseljic +3
Deep active learning (DAL) seeks to reduce annotation costs by enabling the model to actively query instance annotations from which it expects to learn the most. Despite extensive…
Multi-annotator Deep Learning: A Probabilistic Framework for Classification
Marek Herde, Denis Huseljic, Bernhard Sick
Solving complex classification tasks using deep neural networks typically requires large amounts of annotated data. However, corresponding class labels are noisy when provided by e…
A Review of Uncertainty Calibration in Pretrained Object Detectors
Denis Huseljic, Marek Herde, Mehmet Muejde +1
In the field of deep learning based computer vision, the development of deep object detection has led to unique paradigms (e.g., two-stage or set-based) and architectures (e.g., Fa…
Efficient Bayesian Updates for Deep Active Learning via Laplace Approximations
Denis Huseljic, Marek Herde, Lukas Rauch +5
Deep active learning (AL) selects batches of instances for annotation to avoid retraining deep neural networks (DNNs) after each new label. Employing a naive top- selection can…
A Survey on Cost Types, Interaction Schemes, and Annotator Performance Models in Selection Algorithms for Active Learning in Classification
Marek Herde, Denis Huseljic, Bernhard Sick +1
Pool-based active learning (AL) aims to optimize the annotation process (i.e., labeling) as the acquisition of annotations is often time-consuming and therefore expensive. For this…
Out-of-distribution Detection and Generation using Soft Brownian Offset Sampling and Autoencoders
Felix Möller, Diego Botache, Denis Huseljic +3
Deep neural networks often suffer from overconfidence which can be partly remedied by improved out-of-distribution detection. For this purpose, we propose a novel approach that all…
Toward Optimal Probabilistic Active Learning Using a Bayesian Approach
Daniel Kottke, Marek Herde, Christoph Sandrock +3
Gathering labeled data to train well-performing machine learning models is one of the critical challenges in many applications. Active learning aims at reducing the labeling costs…
Limitations of Assessing Active Learning Performance at Runtime
Daniel Kottke, Jim Schellinger, Denis Huseljic +1
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…