Search Results for author: Denis Huseljic

Found 9 papers, 6 papers with code

Active Label Refinement for Semantic Segmentation of Satellite Images

no code implementations12 Sep 2023 Tuan Pham Minh, Jayan Wijesingha, Daniel Kottke, Marek Herde, Denis Huseljic, Bernhard Sick, Michael Wachendorf, Thomas Esch

Since these initial labels are partially erroneous, we use active learning strategies to cost-efficiently refine the labels in the second step.

Active Learning Segmentation +1

ActiveGLAE: A Benchmark for Deep Active Learning with Transformers

1 code implementation16 Jun 2023 Lukas Rauch, Matthias Aßenmacher, Denis Huseljic, Moritz Wirth, Bernd Bischl, Bernhard Sick

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.

Active Learning

Multi-annotator Deep Learning: A Probabilistic Framework for Classification

1 code implementation5 Apr 2023 Marek Herde, Denis Huseljic, Bernhard Sick

Training standard deep neural networks leads to subpar performances in such multi-annotator supervised learning settings.

Classification

A Review of Uncertainty Calibration in Pretrained Object Detectors

1 code implementation6 Oct 2022 Denis Huseljic, Marek Herde, Mehmet Muejde, Bernhard Sick

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., Faster-RCNN or DETR) which enable outstanding performance on challenging benchmark datasets.

Object object-detection +1

A Survey on Cost Types, Interaction Schemes, and Annotator Performance Models in Selection Algorithms for Active Learning in Classification

no code implementations23 Sep 2021 Marek Herde, Denis Huseljic, Bernhard Sick, Adrian Calma

Therefore, we introduce a general real-world AL strategy as part of a learning cycle and use its elements, e. g., the query and annotator selection algorithm, to categorize about 60 real-world AL strategies.

Active Learning

Toward Optimal Probabilistic Active Learning Using a Bayesian Approach

1 code implementation2 Jun 2020 Daniel Kottke, Marek Herde, Christoph Sandrock, Denis Huseljic, Georg Krempl, Bernhard Sick

Gathering labeled data to train well-performing machine learning models is one of the critical challenges in many applications.

Active Learning

Limitations of Assessing Active Learning Performance at Runtime

no code implementations29 Jan 2019 Daniel Kottke, Jim Schellinger, Denis Huseljic, Bernhard Sick

Hence, it is not possible to reliably estimate the performance of the classification system during learning and it is difficult to decide when the system fulfills the quality requirements (stopping criteria).

Active Learning General Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.