Simon-Martin Schröder

• Master of Science
• PhD Student at Kiel University

Inpainting images becomes crucial, especially when dealing with the challenging LOKI zooplankton dataset. This research presents a novel framework for image inpainting, designed to optimize results through a systematic approach. Our proposed framework effectively addresses these challenges, enhancing both the qualitative and quantitative aspects of...

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 usually presumed, while acquiring high-quality datasets is still a major issue in many cases. Subjective annotations by annotators often lead to ambiguous labels in real-wo...

Plankton imaging systems supported by automated classification and analysis have improved ecologists' ability to observe aquatic ecosystems. Today, we are on the cusp of reliably tracking plankton populations with a suite of lab‐based and in situ tools, collecting imaging data at unprecedentedly fine spatial and temporal scales. But these data have...

Image annotation is a time-consuming and costly task. Previously, we published MorphoCluster as a novel image annotation tool to address problems of conventional, classifier-based image annotation approaches: their limited efficiency, training set bias and lack of novelty detection. MorphoCluster uses clustering and similarity search to enable effi...

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 and consistently labeled datasets. Although current approaches in semi-supervised learning can decrease the required amount of annotated data by a factor of 10 or even m...

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 and consistently labeled datasets. Although current approaches in semi-supervised learning can decrease the required amount of annotated data by a factor of 10 or even m...

Midwater marine environments are one of the largest ecosystems on earth. Collecting visual data of a quality from which identifications can be made is difficult due to limited survey opportunities. Often during dives, long video recordings are made, which need to be analyzed in real-time or in post processing for annotating observations. Although m...

Semi-Supervised Learning (SSL) can decrease the amount of required labeled image data and thus the cost for deep learning. Most SSL methods only consider a clear distinction between classes but in many real-world datasets, this clear distinction is not given due to intra- or interobserver variability. This variability can lead to different annotati...

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 many real-world problems, it is not feasible to create such an amount of labeled training data. Therefore, it is common to incorporate unlabeled data into the training proce...

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 required amount of annotated data by a factor of 10 or even more, this line of research still uses distinct classes like cats and dogs. However, in the real-world we often encou...

In this work, we present MorphoCluster, a software tool for data-driven, fast, and accurate annotation of large image data sets. While already having surpassed the annotation rate of human experts, volume and complexity of marine data will continue to increase in the coming years. Still, this data requires interpretation. MorphoCluster augments the...

In this work, we present MorphoCluster, a software tool for data-driven, fast and accurate annotation of large image data sets. While already having surpassed the annotation rate of human experts, volume and complexity of marine data will continue to increase in the coming years. Still, this data requires interpretation. MorphoCluster augments the...

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 many real-world problems, it is not feasible to create such an amount of labeled training data. Therefore, it is common to incorporate unlabeled data into the training proce...

The size of current plankton image datasets renders manual classification virtually infeasible. The training of models for machine classification is complicated by the fact that a large number of classes consist of only a few examples. We employ the recently introduced weight imprinting technique in order to use the available training data to train...

Gelatinous zooplankton hold key functions in the ocean and have been shown to significantly influence the transport of organic carbon to the deep sea. We discovered a gelatinous, flux‐feeding polychaete of the genus Poeobius in very high abundances in a mesoscale eddy in the tropical Atlantic Ocean, where it co‐occurred with extremely low particle...