Moritz Wirth
YOU?
Author Swipe
View article: No Free Lunch in Active Learning: LLM Embedding Quality Dictates Query Strategy Success
No Free Lunch in Active Learning: LLM Embedding Quality Dictates Query Strategy Success Open
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 LLM embeddings, we can mitigate the computational costs of …
View article: Towards Deep Active Learning in Avian Bioacoustics
Towards Deep Active Learning in Avian Bioacoustics Open
Passive acoustic monitoring (PAM) in avian bioacoustics enables cost-effective and extensive data collection with minimal disruption to natural habitats. Despite advancements in computational avian bioacoustics, deep learning models contin…
View article: BirdSet: A Large-Scale Dataset for Audio Classification in Avian Bioacoustics
BirdSet: A Large-Scale Dataset for Audio Classification in Avian Bioacoustics Open
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 domains. While AudioSet is a pivotal step to bridge this gap as …
View article: Active Bird2Vec: Towards End-to-End Bird Sound Monitoring with Transformers
Active Bird2Vec: Towards End-to-End Bird Sound Monitoring with Transformers Open
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 bypass traditional spectrogram conversions, enabling direct…
View article: ActiveGLAE: A Benchmark for Deep Active Learning with Transformers
ActiveGLAE: A Benchmark for Deep Active Learning with Transformers Open
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 research, there is currently no standardized evaluation pro…