• Publications
  • Influence
Distortion Invariant Object Recognition in the Dynamic Link Architecture
An object recognition system based on the dynamic link architecture, an extension to classical artificial neural networks (ANNs), is presented and the implementation on a transputer network achieved recognition of human faces and office objects from gray-level camera images.
Stability-Based Validation of Clustering Solutions
A measure of cluster stability is introduced to assess the validity of a cluster model and its suitability as a general validation tool for clustering solutions in real-world problems.
Guaranteed Non-convex Optimization: Submodular Maximization over Continuous Domains
The weak DR property is introduced that gives a unified characterization of submodularity for all set, integer-lattice and continuous functions and for maximizing monotone DR-submodular continuous functions under general down-closed convex constraints, a Frank-Wolfe variant with approximation guarantee, and sub-linear convergence rate are proposed.
The Balanced Accuracy and Its Posterior Distribution
It is shown that both problems can be overcome by replacing the conventional point estimate of accuracy by an estimate of the posterior distribution of the balanced accuracy.
Weakly supervised semantic segmentation with a multi-image model
A novel method for weakly supervised semantic segmentation using a multi-image model (MIM) - a graphical model for recovering the pixel labels of the training images and introducing an “objectness” potential, that helps separating objects from background classes.
Guarantees for Greedy Maximization of Non-submodular Functions with Applications
It is proved that GREEDY enjoys a tight approximation guarantee of 1/α (1 - e-γα) for cardinality constrained maximization and the submod-ularity ratio and curvature is bound for several important real-world objectives, including the Bayesian A-optimality objective and certain linear programs with combinatorial constraints.
Crowdsourcing the creation of image segmentation algorithms for connectomics
To stimulate progress in automating the reconstruction of neural circuits, we organized the first international challenge on 2D segmentation of electron microscopic (EM) images of the brain.
Empirical evaluation of dissimilarity measures for color and texture
It is demonstrated how the selection of a measure, based on large scale evaluation, substantially improves the quality of classification, retrieval, and unsupervised segmentation of color and texture images.
Pairwise Data Clustering by Deterministic Annealing
A deterministic annealing approach to pairwise clustering is described which shares the robustness properties of maximum entropy inference and the resulting Gibbs probability distributions are estimated by mean-field approximation.
TI-POOLING: Transformation-Invariant Pooling for Feature Learning in Convolutional Neural Networks
A deep neural network topology that incorporates a simple to implement transformationinvariant pooling operator (TI-POOLING) that is able to efficiently handle prior knowledge on nuisance variations in the data, such as rotation or scale changes is presented.