Search Results for author:
Found 31 papers, 6 papers with code
HAct: Out-of-Distribution Detection with Neural Net Activation Histograms
We propose a simple, efficient, and accurate method for detecting out-of-distribution (OOD) data for trained neural networks.
StEik: Stabilizing the Optimization of Neural Signed Distance Functions and Finer Shape Representation
We show analytically that as the representation power of the network increases, the optimization approaches a partial differential equation (PDE) in the continuum limit that is unstable.
Surprising Instabilities in Training Deep Networks and a Theoretical Analysis
We discover restrained numerical instabilities in current training practices of deep networks with stochastic gradient descent (SGD).
Accelerated PDEs for Construction and Theoretical Analysis of an SGD Extension
We introduce a recently developed framework PDE Acceleration, which is a variational approach to accelerated optimization with partial differential equations (PDE), in the context of optimization of deep networks.
Shape-Tailored Deep Neural Networks With PDEs
ST-DNN are deep networks formulated through the use of partial differential equations (PDE) to be defined on arbitrarily shaped regions.
Flow-Guided Video Inpainting with Scene Templates
We consider the problem of filling in missing spatio-temporal regions of a video.
Class-Agnostic Segmentation Loss and Its Application to Salient Object Detection and Segmentation
For low-fidelity training data (incorrect class label) class-agnostic segmentation loss outperforms the state-of-the-art methods on salient object detection datasets by staggering margins of around 50%.
Shape-Tailored Deep Neural Networks
We stack multiple PDE layers to generalize a deep CNN to arbitrary regions, and apply it to segmentation.
Shape-Tailored Deep Neural Networks Using PDEs for Segmentation
We present Shape-Tailored Deep Neural Networks (ST-DNN).
Class-Agnostic Segmentation Loss and Its Application to Salient Object Detection and Segmentation
For low-fidelity training data (incorrect class label) class-agnostic segmentation loss outperforms the state-of-the-art methods on salient object detection datasets by staggering margins of around 50%.
Channel-Directed Gradients for Optimization of Convolutional Neural Networks
We introduce optimization methods for convolutional neural networks that can be used to improve existing gradient-based optimization in terms of generalization error.
Phase Consistent Ecological Domain Adaptation
We introduce two criteria to regularize the optimization involved in learning a classifier in a domain where no annotated data are available, leveraging annotated data in a different domain, a problem known as unsupervised domain adaptation.
Translation Insensitive CNNs
This is shown to be invariant to small shifts, and preserves the efficiency of training.
Minimum Delay Object Detection From Video
We consider the problem of detecting objects, as they come into view, from videos in an online fashion.
Variational PDEs for Acceleration on Manifolds and Application to Diffeomorphisms
Our approach evolves an infinite number of particles endowed with mass, represented as a mass density.
Extending Layered Models to 3D Motion
We consider the problem of inferring a layered representa-tion, its depth ordering and motion segmentation from a video in whichobjects may undergo 3D non-planar motion relative to the camera.
Learned Shape-Tailored Descriptors for Segmentation
We formulate and optimize a joint optimization problem in the segmentation and descriptors to discriminate these base descriptors using the learned metric, equivalent to grouping learned descriptors.
Accelerated Optimization in the PDE Framework: Formulations for the Manifold of Diffeomorphisms
We present a new class of optimization methods, valid for any optimization problem setup on the space of diffeomorphisms by generalizing Nesterov accelerated optimization to the manifold of diffeomorphisms.
Accelerated Optimization in the PDE Framework: Formulations for the Active Contour Case
Following the seminal work of Nesterov, accelerated optimization methods have been used to powerfully boost the performance of first-order, gradient-based parameter estimation in scenarios where second-order optimization strategies are either inapplicable or impractical.
Minimum Delay Moving Object Detection
Our method is designed to detect the object(s) with minimum delay, i. e., frames after the object moves, constraining the false alarms.
Coarse-To-Fine Segmentation With Shape-Tailored Continuum Scale Spaces
We formulate an energy for segmentation that is designed to have preference for segmenting the coarse over fine structure of the image, without smoothing across boundaries of regions.
SurfCut: Surfaces of Minimal Paths From Topological Structures
We present SurfCut, an algorithm for extracting a smooth, simple surface with an unknown 3D curve boundary from a noisy 3D image and a seed point.
Quickest Moving Object Detection
We present a general framework and method for simultaneous detection and segmentation of an object in a video that moves (or comes into view of the camera) at some unknown time in the video.
Coarse-to-Fine Segmentation With Shape-Tailored Scale Spaces
We formulate a general energy and method for segmentation that is designed to have preference for segmenting the coarse structure over the fine structure of the data, without smoothing across boundaries of regions.
Self-Occlusions and Disocclusions in Causal Video Object Segmentation
We propose a method to detect disocclusion in video sequences of three-dimensional scenes and to partition the disoccluded regions into objects, defined by coherent deformation corresponding to surfaces in the scene.
Shape-Tailored Local Descriptors and Their Application to Segmentation and Tracking
Given a region of arbitrary shape in an image, these descriptors are formed from shape-dependent scale spaces of oriented gradients.
FAST LABEL: Easy and Efficient Solution of Joint Multi-Label and Estimation Problems
We derive an easy-to-implement and efficient algorithm for solving multi-label image partitioning problems in the form of the problem addressed by Region Competition.
Tracking via Motion Estimation with Physically Motivated Inter-Region Constraints
We illustrate the use of this motion estimation scheme in propagating a segmentation across frames and show that it leads to more accurate segmentation than traditional motion estimation that does not make use of physical constraints.
A New Model and Simple Algorithms for Multi-label Mumford-Shah Problems
The advantage of this statistical model is that the underlying variables: the labels and the functions are less coupled than in the original formulation, and the labels can be computed from the functions with more global updates.
Shape Tracking With Occlusions via Coarse-To-Fine Region-Based Sobolev Descent
In cases of 3D object motion and viewpoint change, self-occlusions and dis-occlusions of the object are prominent, and current methods employing joint shape and appearance models are unable to adapt to new shape and appearance information, leading to inaccurate shape detection.
