Search Results for author: Fred A. Hamprecht

Found 34 papers, 18 papers with code

Joint Semantic Instance Segmentation on Graphs with the Semantic Mutex Watershed

no code implementations ECCV 2020 Steffen Wolf, Yuyan Li, Constantin Pape, Alberto Bailoni, Anna Kreshuk, Fred A. Hamprecht

Semantic instance segmentation is the task of simultaneously partitioning an image into distinct segments while associating each pixel with a class label.

graph partitioning Instance Segmentation +2

Contrastive learning unifies $t$-SNE and UMAP

1 code implementation3 Jun 2022 Sebastian Damrich, Jan Niklas Böhm, Fred A. Hamprecht, Dmitry Kobak

Neighbor embedding methods $t$-SNE and UMAP are the de facto standard for visualizing high-dimensional datasets.

Contrastive Learning Representation Learning

Directed Probabilistic Watershed

1 code implementation NeurIPS 2021 Enrique Fita Sanmartin, Sebastian Damrich, Fred A. Hamprecht

We propose the "Directed Probabilistic Watershed", an extension of the Probabilistic Watershed algorithm to directed graphs.

Extensions of Karger's Algorithm: Why They Fail in Theory and How They Are Useful in Practice

no code implementations ICCV 2021 Erik Jenner, Enrique Fita Sanmartín, Fred A. Hamprecht

However, we then present a simple new algorithm for seeded segmentation / graph-based semi-supervised learning that is closely based on Karger's original algorithm, showing that for these problems, extensions of Karger's algorithm can be useful.

Gaussian Processes Semantic Segmentation

On UMAP's true loss function

1 code implementation NeurIPS 2021 Sebastian Damrich, Fred A. Hamprecht

As a consequence, we show that UMAP does not aim to reproduce its theoretically motivated high-dimensional UMAP similarities.

Proposal-Free Volumetric Instance Segmentation from Latent Single-Instance Masks

no code implementations10 Sep 2020 Alberto Bailoni, Constantin Pape, Steffen Wolf, Anna Kreshuk, Fred A. Hamprecht

This work introduces a new proposal-free instance segmentation method that builds on single-instance segmentation masks predicted across the entire image in a sliding window style.

Instance Segmentation Semantic Segmentation

Instance Separation Emerges from Inpainting

no code implementations28 Feb 2020 Steffen Wolf, Fred A. Hamprecht, Jan Funke

Deep neural networks trained to inpaint partially occluded images show a deep understanding of image composition and have even been shown to remove objects from images convincingly.

The Semantic Mutex Watershed for Efficient Bottom-Up Semantic Instance Segmentation

no code implementations29 Dec 2019 Steffen Wolf, Yuyan Li, Constantin Pape, Alberto Bailoni, Anna Kreshuk, Fred A. Hamprecht

Semantic instance segmentation is the task of simultaneously partitioning an image into distinct segments while associating each pixel with a class label.

graph partitioning Instance Segmentation +2

Probabilistic Watershed: Sampling all spanning forests for seeded segmentation and semi-supervised learning

1 code implementation NeurIPS 2019 Enrique Fita Sanmartin, Sebastian Damrich, Fred A. Hamprecht

The seeded Watershed algorithm / minimax semi-supervised learning on a graph computes a minimum spanning forest which connects every pixel / unlabeled node to a seed / labeled node.

DISCo: Deep learning, Instance Segmentation, and Correlations for cell segmentation in calcium imaging

1 code implementation21 Aug 2019 Elke Kirschbaum, Alberto Bailoni, Fred A. Hamprecht

In order to use the data gained with calcium imaging, it is necessary to extract individual cells and their activity from the recordings.

Cell Segmentation Instance Segmentation +1

GASP, a generalized framework for agglomerative clustering of signed graphs and its application to Instance Segmentation

no code implementations CVPR 2022 Alberto Bailoni, Constantin Pape, Nathan Hütsch, Steffen Wolf, Thorsten Beier, Anna Kreshuk, Fred A. Hamprecht

We propose a theoretical framework that generalizes simple and fast algorithms for hierarchical agglomerative clustering to weighted graphs with both attractive and repulsive interactions between the nodes.

graph partitioning Instance Segmentation +2

Deep Active Learning with Adaptive Acquisition

1 code implementation27 Jun 2019 Manuel Haussmann, Fred A. Hamprecht, Melih Kandemir

As active learning is a scarce data regime, we bootstrap from a well-known heuristic that filters the bulk of data points on which all heuristics would agree, and learn a policy to warp the top portion of this ranking in the most beneficial way for the character of a specific data distribution.

Active Learning Model Selection

The Mutex Watershed and its Objective: Efficient, Parameter-Free Graph Partitioning

no code implementations25 Apr 2019 Steffen Wolf, Alberto Bailoni, Constantin Pape, Nasim Rahaman, Anna Kreshuk, Ullrich Köthe, Fred A. Hamprecht

Unlike seeded watershed, the algorithm can accommodate not only attractive but also repulsive cues, allowing it to find a previously unspecified number of segments without the need for explicit seeds or a tunable threshold.

graph partitioning

LeMoNADe: Learned Motif and Neuronal Assembly Detection in calcium imaging videos

1 code implementation ICLR 2019 Elke Kirschbaum, Manuel Haußmann, Steffen Wolf, Hannah Jakobi, Justus Schneider, Shehabeldin Elzoheiry, Oliver Kann, Daniel Durstewitz, Fred A. Hamprecht

Neuronal assemblies, loosely defined as subsets of neurons with reoccurring spatio-temporally coordinated activation patterns, or "motifs", are thought to be building blocks of neural representations and information processing.

On the Spectral Bias of Neural Networks

2 code implementations ICLR 2019 Nasim Rahaman, Aristide Baratin, Devansh Arpit, Felix Draxler, Min Lin, Fred A. Hamprecht, Yoshua Bengio, Aaron Courville

Neural networks are known to be a class of highly expressive functions able to fit even random input-output mappings with $100\%$ accuracy.

Sampling-Free Variational Inference of Bayesian Neural Networks by Variance Backpropagation

1 code implementation19 May 2018 Manuel Haussmann, Fred A. Hamprecht, Melih Kandemir

We propose a new Bayesian Neural Net formulation that affords variational inference for which the evidence lower bound is analytically tractable subject to a tight approximation.

Variational Inference

Diverse M-Best Solutions by Dynamic Programming

no code implementations15 Mar 2018 Carsten Haubold, Virginie Uhlmann, Michael Unser, Fred A. Hamprecht

Many computer vision pipelines involve dynamic programming primitives such as finding a shortest path or the minimum energy solution in a tree-shaped probabilistic graphical model.

object-detection Object Detection

Essentially No Barriers in Neural Network Energy Landscape

2 code implementations ICML 2018 Felix Draxler, Kambis Veschgini, Manfred Salmhofer, Fred A. Hamprecht

Training neural networks involves finding minima of a high-dimensional non-convex loss function.

End-to-end Learning of Deterministic Decision Trees

1 code implementation7 Dec 2017 Thomas Hehn, Fred A. Hamprecht

Conventional decision trees have a number of favorable properties, including interpretability, a small computational footprint and the ability to learn from little training data.

Cost efficient gradient boosting

1 code implementation NeurIPS 2017 Sven Peter, Ferran Diego, Fred A. Hamprecht, Boaz Nadler

In contrast to previous approaches to learning with cost penalties, our method can grow very deep trees that on average are nonetheless cheap to compute.

Sparse convolutional coding for neuronal assembly detection

1 code implementation NeurIPS 2017 Sven Peter, Elke Kirschbaum, Martin Both, Lee Campbell, Brandon Harvey, Conor Heins, Daniel Durstewitz, Ferran Diego, Fred A. Hamprecht

Cell assemblies, originally proposed by Donald Hebb (1949), are subsets of neurons firing in a temporally coordinated way that gives rise to repeated motifs supposed to underly neural representations and information processing.

Fusion Moves for Correlation Clustering

1 code implementation CVPR 2015 Thorsten Beier, Fred A. Hamprecht, Jorg H. Kappes

Correlation clustering, or multicut partitioning, is widely used in image segmentation for partitioning an undirected graph or image with positive and negative edge weights such that the sum of cut edge weights is minimized.

Semantic Segmentation

Sparse Space-Time Deconvolution for Calcium Image Analysis

no code implementations NeurIPS 2014 Ferran Diego Andilla, Fred A. Hamprecht

Experiments on real and synthetic data demonstrate the viability of the proposed method.

Tracking Indistinguishable Translucent Objects over Time using Weakly Supervised Structured Learning

no code implementations CVPR 2014 Luca Fiaschi, Ferran Diego, Konstantin Gregor, Martin Schiegg, Ullrich Koethe, Marta Zlatic, Fred A. Hamprecht

We use weakly supervised structured learning to track and disambiguate the identity of multiple indistinguishable, translucent and deformable objects that can overlap for many frames.

Cut, Glue & Cut: A Fast, Approximate Solver for Multicut Partitioning

no code implementations CVPR 2014 Thorsten Beier, Thorben Kroeger, Jorg H. Kappes, Ullrich Kothe, Fred A. Hamprecht

Since this problem is NP-hard, we propose a new approximate solver based on the move-making paradigm: first, the graph is recursively partitioned into small regions (cut phase).

Semantic Segmentation Unsupervised Image Segmentation

A Comparative Study of Modern Inference Techniques for Structured Discrete Energy Minimization Problems

no code implementations2 Apr 2014 Jörg H. Kappes, Bjoern Andres, Fred A. Hamprecht, Christoph Schnörr, Sebastian Nowozin, Dhruv Batra, Sungwoong Kim, Bernhard X. Kausler, Thorben Kröger, Jan Lellmann, Nikos Komodakis, Bogdan Savchynskyy, Carsten Rother

However, on new and challenging types of models our findings disagree and suggest that polyhedral methods and integer programming solvers are competitive in terms of runtime and solution quality over a large range of model types.

Learning Multi-level Sparse Representations

no code implementations NeurIPS 2013 Ferran Diego Andilla, Fred A. Hamprecht

In some applications, however, there is a natural hierarchy of concepts that ought to be reflected in the unsupervised analysis.

Structured Learning for Cell Tracking

no code implementations NeurIPS 2011 Xinghua Lou, Fred A. Hamprecht

We study the problem of learning to track a large quantity of homogeneous objects such as cell tracking in cell culture study and developmental biology.

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