5 citations · 13 across the 13 of their papers we have counts for
15 papers
BioDCASE: Active Learning for Bioacoustics
Ben McEwen, Rupa Kurinchi-Vendhan, Shiqi Zhang +3
Ecological monitoring increasingly relies on machine learning models, whose performance depends on the quality and quantity of labelled data. However, obtaining these labels is cos…
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…
Unmute the Patch Tokens: Rethinking Probing in Multi-Label Audio Classification
Lukas Rauch, René Heinrich, Houtan Ghaffari +4
Although probing frozen models has become a standard evaluation paradigm, self-supervised learning in audio defaults to fine-tuning when pursuing state-of-the-art on AudioSet. A ke…
Hashing-Baseline: Rethinking Hashing in the Age of Pretrained Models
Ilyass Moummad, Kawtar Zaher, Lukas Rauch +1
Information retrieval with compact binary embeddings, also referred to as hashing, is crucial for scalable fast search applications, yet state-of-the-art hashing methods require ex…
Adversarial Training Improves Generalization Under Distribution Shifts in Bird Sound Classification
René Heinrich, Lukas Rauch, Raphael Schwinger +4
Adversarial training is a promising strategy for enhancing robustness against adversarial attacks, but its impact on generalization under substantial distribution shifts in audio c…
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…
Can Masked Autoencoders Also Listen to Birds?
Lukas Rauch, René Heinrich, Ilyass Moummad +3
Masked Autoencoders (MAEs) learn rich semantic representations in audio classification through an efficient self-supervised reconstruction task. However, general-purpose models fai…
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…
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 Bird2Vec: Towards End-to-End Bird Sound Monitoring with Transformers
Lukas Rauch, Raphael Schwinger, Moritz Wirth +3
We propose a shift towards end-to-end learning in bird sound monitoring by combining self-supervised (SSL) and deep active learning (DAL). Leveraging transformer models, we aim to…
DADO -- Low-Cost Query Strategies for Deep Active Design Optimization
Jens Decke, Christian Gruhl, Lukas Rauch +1
In this experience report, we apply deep active learning to the field of design optimization to reduce the number of computationally expensive numerical simulations. We are interes…
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…
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…