Search Results for author:
Found 38 papers, 20 papers with code
Joint Semantic Instance Segmentation on Graphs with the Semantic Mutex Watershed
Semantic instance segmentation is the task of simultaneously partitioning an image into distinct segments while associating each pixel with a class label.
The Central Spanning Tree Problem
Spanning trees are an important primitive in many data analysis tasks, when a data set needs to be summarized in terms of its "skeleton", or when a tree-shaped graph over all observations is required for downstream processing.
Geometric Autoencoders -- What You See is What You Decode
Visualization is a crucial step in exploratory data analysis.
KineticNet: Deep learning a transferable kinetic energy functional for orbital-free density functional theory
We here set out to learn the kinetic energy functional from ground truth provided by the more expensive Kohn-Sham density functional theory.
Theory and Approximate Solvers for Branched Optimal Transport with Multiple Sources
We here study the NP-hard optimization of BOT networks connecting a finite number of sources and sinks in $\mathbb{R}^2$.
From $t$-SNE to UMAP with contrastive learning
We exploit this new conceptual connection to propose and implement a generalization of negative sampling, allowing us to interpolate between (and even extrapolate beyond) $t$-SNE and UMAP and their respective embeddings.
CellTypeGraph: A New Geometric Computer Vision Benchmark
Classifying all cells in an organ is a relevant and difficult problem from plant developmental biology.
Ranked #1 on
Node Classification
on CellTypeGraph Benchmark
Directed Probabilistic Watershed
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
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.
On UMAP's true loss function
As a consequence, we show that UMAP does not aim to reproduce its theoretically motivated high-dimensional UMAP similarities.
MultiStar: Instance Segmentation of Overlapping Objects with Star-Convex Polygons
Instance segmentation of overlapping objects in biomedical images remains a largely unsolved problem.
Proposal-Free Volumetric Instance Segmentation from Latent Single-Instance Masks
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 Separation Emerges from Inpainting
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
Semantic instance segmentation is the task of simultaneously partitioning an image into distinct segments while associating each pixel with a class label.
Probabilistic Watershed: Sampling all spanning forests for seeded segmentation and semi-supervised learning
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
In order to use the data gained with calcium imaging, it is necessary to extract individual cells and their activity from the recordings.
Deep Active Learning with Adaptive Acquisition
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.
GASP, a generalized framework for agglomerative clustering of signed graphs and its application to Instance Segmentation
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.
End-to-End Learned Random Walker for Seeded Image Segmentation
We present an end-to-end learned algorithm for seeded segmentation.
The Mutex Watershed and its Objective: Efficient, Parameter-Free Graph Partitioning
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.
LeMoNADe: Learned Motif and Neuronal Assembly Detection in calcium imaging videos
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
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
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.
Diverse M-Best Solutions by Dynamic Programming
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.
Essentially No Barriers in Neural Network Energy Landscape
Training neural networks involves finding minima of a high-dimensional non-convex loss function.
End-to-end Learning of Deterministic Decision Trees
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
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
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.
Learning Steerable Filters for Rotation Equivariant CNNs
In many machine learning tasks it is desirable that a model's prediction transforms in an equivariant way under transformations of its input.
Ranked #2 on
Breast Tumour Classification
on PCam
Breast Tumour Classification
Colorectal Gland Segmentation:
+2
Variational Bayesian Multiple Instance Learning With Gaussian Processes
Gaussian Processes (GPs) are effective Bayesian predictors.
Structured Regression Gradient Boosting
We propose a new way to train a structured output prediction model.
Fusion Moves for Correlation Clustering
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.
Sparse Space-Time Deconvolution for Calcium Image Analysis
Experiments on real and synthetic data demonstrate the viability of the proposed method.
Tracking Indistinguishable Translucent Objects over Time using Weakly Supervised Structured Learning
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
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).
A Comparative Study of Modern Inference Techniques for Structured Discrete Energy Minimization Problems
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
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
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.
