3.1k citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Janelia Research CampusUS53 papers
- Rockefeller UniversityUS28 papers
- Harvard UniversityUS27 papers
- University of California, BerkeleyUS26 papers
- Princeton UniversityUS20 papers
- Northwestern UniversityUS17 papers
- California Institute of TechnologyUS16 papers
- Massachusetts Institute of TechnologyUS16 papers
- Stanford UniversityUS14 papers
- New York UniversityUS13 papers
- University of ChicagoUS13 papers
- Centre National de la Recherche ScientifiqueFR12 papers
18 papers · 1 filter
DivShift: Exploring Domain-Specific Distribution Shifts in Large-Scale, Volunteer-Collected Biodiversity Datasets
Elena Sierra, Lauren E. Gillespie, Salim Soltani +2
Large-scale, volunteer-collected datasets of community-identified natural world imagery like iNaturalist have enabled marked performance gains for fine-grained visual classificatio…
The Animation Transformer: Visual Correspondence via Segment Matching
Evan Casey, Víctor Pérez, Zhuoru Li +5
Visual correspondence is a fundamental building block on the way to building assistive tools for hand-drawn animation. However, while a large body of work has focused on learning v…
A topological solution to object segmentation and tracking
Thomas Tsao, Doris Y. Tsao
The world is composed of objects, the ground, and the sky. Visual perception of objects requires solving two fundamental challenges: segmenting visual input into discrete units, an…
How Shift Equivariance Impacts Metric Learning for Instance Segmentation
Josef Lorenz Rumberger, Xiaoyan Yu, Peter Hirsch +6
Metric learning has received conflicting assessments concerning its suitability for solving instance segmentation tasks. It has been dismissed as theoretically flawed due to the sh…
Large Scale Image Segmentation with Structured Loss based Deep Learning for Connectome Reconstruction
Jan Funke, Fabian David Tschopp, William Grisaitis +4
We present a method combining affinity prediction with region agglomeration, which improves significantly upon the state of the art of neuron segmentation from electron microscopy…
Deep Learning for Isotropic Super-Resolution from Non-Isotropic 3D Electron Microscopy
Larissa Heinrich, John A. Bogovic, Stephan Saalfeld
The most sophisticated existing methods to generate 3D isotropic super-resolution (SR) from non-isotropic electron microscopy (EM) are based on learned dictionaries. Unfortunately,…
Robust Registration of Calcium Images by Learned Contrast Synthesis
John A. Bogovic, Philipp Hanslovsky, Allan Wong +1
Multi-modal image registration is a challenging task that is vital to fuse complementary signals for subsequent analyses. Despite much research into cost functions addressing this…
Geodesics of learned representations
Olivier J. Hénaff, Eero P. Simoncelli
We develop a new method for visualizing and refining the invariances of learned representations. Specifically, we test for a general form of invariance, linearization, in which the…
TED: A Tolerant Edit Distance for Segmentation Evaluation
Jan Funke, Francesc Moreno-Noguer, Albert Cardona +1
In this paper, we present a novel error measure to compare a segmentation against ground truth. This measure, which we call Tolerant Edit Distance (TED), is motivated by two observ…
The local low-dimensionality of natural images
Olivier J. Hénaff, Johannes Ballé, Neil C. Rabinowitz +1
We develop a new statistical model for photographic images, in which the local responses of a bank of linear filters are described as jointly Gaussian, with zero mean and a covaria…
Post-acquisition image based compensation for thickness variation in microscopy section series
Philipp Hanslovsky, John A. Bogovic, Stephan Saalfeld
Serial section Microscopy is an established method for volumetric anatomy reconstruction. Section series imaged with Electron Microscopy are currently vital for the reconstruction…
Small Sample Learning of Superpixel Classifiers for EM Segmentation- Extended Version
Toufiq Parag, Stephen Plaza, Louis Scheffer
Pixel and superpixel classifiers have become essential tools for EM segmentation algorithms. Training these classifiers remains a major bottleneck primarily due to the requirement…
A Context-aware Delayed Agglomeration Framework for Electron Microscopy Segmentation
Toufiq Parag, Anirban Chakraborty, Stephen Plaza +1
Electron Microscopy (EM) image (or volume) segmentation has become significantly important in recent years as an instrument for connectomics. This paper proposes a novel agglomerat…
Learned versus Hand-Designed Feature Representations for 3d Agglomeration
John A. Bogovic, Gary B. Huang, Viren Jain
For image recognition and labeling tasks, recent results suggest that machine learning methods that rely on manually specified feature representations may be outperformed by method…
Deep and Wide Multiscale Recursive Networks for Robust Image Labeling
Gary B. Huang, Viren Jain
Feedforward multilayer networks trained by supervised learning have recently demonstrated state of the art performance on image labeling problems such as boundary prediction and sc…
Submodularity of a Set Label Disagreement Function
Toufiq Parag
A set label disagreement function is defined over the number of variables that deviates from the dominant label. The dominant label is the value assumed by the largest number of va…
Machine learning of hierarchical clustering to segment 2D and 3D images
Juan Nunez-Iglesias, Ryan Kennedy, Toufiq Parag +2
We aim to improve segmentation through the use of machine learning tools during region agglomeration. We propose an active learning approach for performing hierarchical agglomerati…
Fast approximations to structured sparse coding and applications to object classification
Arthur Szlam, Karol Gregor, Yann LeCun
We describe a method for fast approximation of sparse coding. The input space is subdivided by a binary decision tree, and we simultaneously learn a dictionary and assignment of al…