Learning Topological Representations for Deep Image Understanding
In many scenarios, especially biomedical applications, the correct delineation of complex fine-scaled structures such as neurons, tissues, and vessels is critical for downstream analysis. Despite the strong predictive power of deep learning methods, they do not provide a satisfactory representation of these structures, thus creating significant barriers in scalable annotation and downstream analysis. In this dissertation, we tackle such challenges by proposing novel representations of these topological structures in a deep learning framework. We leverage the mathematical tools from topological data analysis, i.e., persistent homology and discrete Morse theory, to develop principled methods for better segmentation and uncertainty estimation, which will become powerful tools for scalable annotation.
Code (0)
등록된 구현이 없습니다.
Tasks
Deep LearningTopological Data AnalysisSimilar Papers 제목 키워드 기반
Topological Representational Similarity Analysis in Brains and Beyond
Understanding how the brain represents and processes information is crucial for advancing neuroscience and artificial intelligence. Representational similarity analysis (RSA) has been instrumental in characterizing neura…
Time Series AnalysisTopological Data AnalysisDo Neural Networks Trained with Topological Features Learn Different Internal Representations?
There is a growing body of work that leverages features extracted via topological data analysis to train machine learning models. While this field, sometimes known as topological machine learning (TML), has seen some not…
Topological Data AnalysisOPAL: Encoding Causal Understanding of Physical Systems for Robot Learning
We present OPAL (Operant Physical Agent with Language), a novel vision-language-action architecture that introduces topological constraints to flow matching for robotic control. To do so, we further introduce topological…
Vision-Language-ActionClassification of Firn Data via Topological Features
In this paper we evaluate the performance of topological features for generalizable and robust classification of firn image data, with the broader goal of understanding the advantages, pitfalls, and trade-offs in topolog…
ClassificationRobust classificationTopological Data AnalysisTopological Autoencoders
We propose a novel approach for preserving topological structures of the input space in latent representations of autoencoders. Using persistent homology, a technique from topological data analysis, we calculate topologi…
Data AugmentationTopological Data Analysis