219 citations · 248 across the 6 of their papers we have counts for
7 papers
Don't Mind the Gaps: Implicit Neural Representations for Resolution-Agnostic Retinal OCT Analysis
Bennet Kahrs, Julia Andresen, Fenja Falta +3
Routine clinical imaging of the retina using optical coherence tomography (OCT) is performed with large slice spacing, resulting in highly anisotropic images and a sparsely scanned…
Label Smarter, Not Harder: CleverLabel for Faster Annotation of Ambiguous Image Classification with Higher Quality
Lars Schmarje, Vasco Grossmann, Tim Michels +4
High-quality data is crucial for the success of machine learning, but labeling large datasets is often a time-consuming and costly process. While semi-supervised learning can help…
Fuzzy Overclustering: Semi-Supervised Classification of Fuzzy Labels with Overclustering and Inverse Cross-Entropy
Lars Schmarje, Johannes Brünger, Monty Santarossa +3
Deep learning has been successfully applied to many classification problems including underwater challenges. However, a long-standing issue with deep learning is the need for large…
Learning Stixel-based Instance Segmentation
Monty Santarossa, Lukas Schneider, Claudius Zelenka +3
Stixels have been successfully applied to a wide range of vision tasks in autonomous driving, recently including instance segmentation. However, due to their sparse occurrence in t…
A data-centric approach for improving ambiguous labels with combined semi-supervised classification and clustering
Lars Schmarje, Monty Santarossa, Simon-Martin Schröder +5
Consistently high data quality is essential for the development of novel loss functions and architectures in the field of deep learning. The existence of such data and labels is us…
Beyond Cats and Dogs: Semi-supervised Classification of fuzzy labels with overclustering
Lars Schmarje, Johannes Brünger, Monty Santarossa +3
A long-standing issue with deep learning is the need for large and consistently labeled datasets. Although the current research in semi-supervised learning can decrease the require…
A survey on Semi-, Self- and Unsupervised Learning for Image Classification
Lars Schmarje, Monty Santarossa, Simon-Martin Schröder +1
While deep learning strategies achieve outstanding results in computer vision tasks, one issue remains: The current strategies rely heavily on a huge amount of labeled data. In man…