Search Results for author:
Found 51 papers, 22 papers with code
Robustness and Exploration of Variational and Machine Learning Approaches to Inverse Problems: An Overview
This paper attempts to provide an overview of current approaches for solving inverse problems in imaging using variational methods and machine learning.
Evaluating Adversarial Robustness of Low dose CT Recovery
Both classical approaches and deep networks are affected by such attacks leading to changes in the visual appearance of localized lesions, for extremely small perturbations.
Temporal Action Localization for Inertial-based Human Activity Recognition
Our results show that state-of-the-art TAL models are able to outperform popular inertial models on 4 out of 6 wearable activity recognition benchmark datasets, with improvements ranging as much as 25% in F1-score.
SIGMA: Scale-Invariant Global Sparse Shape Matching
We propose a novel mixed-integer programming (MIP) formulation for generating precise sparse correspondences for highly non-rigid shapes.
An Evaluation of Zero-Cost Proxies -- from Neural Architecture Performance to Model Robustness
We are interested in the single prediction task for robustness and the joint multi-objective of clean and robust accuracy.
Differentiable Sensor Layouts for End-to-End Learning of Task-Specific Camera Parameters
The success of deep learning is frequently described as the ability to train all parameters of a network on a specific application in an end-to-end fashion.
WEAR: An Outdoor Sports Dataset for Wearable and Egocentric Activity Recognition
Though research has shown the complementarity of camera- and inertial-based data, datasets which offer both egocentric video and inertial-based sensor data remain scarce.
Egocentric Activity Recognition
Human Activity Recognition
+2
CCuantuMM: Cycle-Consistent Quantum-Hybrid Matching of Multiple Shapes
Jointly matching multiple, non-rigidly deformed 3D shapes is a challenging, $\mathcal{NP}$-hard problem.
Convergent Data-driven Regularizations for CT Reconstruction
The reconstruction of images from their corresponding noisy Radon transform is a typical example of an ill-posed linear inverse problem as arising in the application of computerized tomography (CT).
QuAnt: Quantum Annealing with Learnt Couplings
As a result, the solution encodings can be chosen flexibly and compactly.
On Adversarial Robustness of Deep Image Deblurring
Recent approaches employ deep learning-based solutions for the recovery of a sharp image from its blurry observation.
A Simple Strategy to Provable Invariance via Orbit Mapping
Many applications require robustness, or ideally invariance, of neural networks to certain transformations of input data.
Intrinsic Neural Fields: Learning Functions on Manifolds
Neural fields have gained significant attention in the computer vision community due to their excellent performance in novel view synthesis, geometry reconstruction, and generative modeling.
DARTS for Inverse Problems: a Study on Stability
Differentiable architecture search (DARTS) is a widely researched tool for neural architecture search, due to its promising results for image classification.
Tutorial on Deep Learning for Human Activity Recognition
Activity recognition systems that are capable of estimating human activities from wearable inertial sensors have come a long way in the past decades.
Stochastic Training is Not Necessary for Generalization
It is widely believed that the implicit regularization of SGD is fundamental to the impressive generalization behavior we observe in neural networks.
Is Differentiable Architecture Search truly a One-Shot Method?
In this work, we investigate DAS in a systematic case study of inverse problems, which allows us to analyze these potential benefits in a controlled manner.
Improving Deep Learning for HAR with shallow LSTMs
Recent studies in Human Activity Recognition (HAR) have shown that Deep Learning methods are able to outperform classical Machine Learning algorithms.
Lifting the Convex Conjugate in Lagrangian Relaxations: A Tractable Approach for Continuous Markov Random Fields
In contrast to existing discretizations which suffer from a grid bias, we show that a piecewise polynomial discretization better preserves the continuous nature of our problem.
Adiabatic Quantum Graph Matching with Permutation Matrix Constraints
In this work, we address such problems with emerging quantum computing technology and propose several reformulations of QAPs as unconstrained problems suitable for efficient execution on quantum hardware.
Training or Architecture? How to Incorporate Invariance in Neural Networks
Many applications require the robustness, or ideally the invariance, of a neural network to certain transformations of input data.
Q-Match: Iterative Shape Matching via Quantum Annealing
Finding shape correspondences can be formulated as an NP-hard quadratic assignment problem (QAP) that becomes infeasible for shapes with high sampling density.
What Doesn't Kill You Makes You Robust(er): How to Adversarially Train against Data Poisoning
Data poisoning is a threat model in which a malicious actor tampers with training data to manipulate outcomes at inference time.
Inverting Gradients - How easy is it to break privacy in federated learning?
The idea of federated learning is to collaboratively train a neural network on a server.
Learning Spectral Regularizations for Linear Inverse Problems
One of the main challenges in linear inverse problems is that a majority of such problems are ill-posed in the sense that the solution does not depend on the data continuously.
Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching
We consider a particularly malicious poisoning attack that is both "from scratch" and "clean label", meaning we analyze an attack that successfully works against new, randomly initialized models, and is nearly imperceptible to humans, all while perturbing only a small fraction of the training data.
Exploiting the Logits: Joint Sign Language Recognition and Spell-Correction
We demonstrate that purely learning on softmax inputs in combination with scarce training data yields overfitting as the network learns the inputs by heart.
A Simple Domain Shifting Networkfor Generating Low Quality Images
Deep Learning systems have proven to be extremely successful for image recognition tasks for which significant amounts of training data is available, e. g., on the famous ImageNet dataset.
A Generative Model for Generic Light Field Reconstruction
We develop a generative model conditioned on the central view of the light field and incorporate this as a prior in an energy minimization framework to address diverse light field reconstruction tasks.
Fast Convex Relaxations using Graph Discretizations
We discuss this methodology in detail and show examples in multi-label segmentation by minimal partitions and stereo estimation, where we demonstrate that the proposed graph discretization can reduce runtime as well as memory consumption of convex relaxations of matching problems by up to a factor of 10.
Inverting Gradients -- How easy is it to break privacy in federated learning?
The idea of federated learning is to collaboratively train a neural network on a server.
Truth or Backpropaganda? An Empirical Investigation of Deep Learning Theory
We empirically evaluate common assumptions about neural networks that are widely held by practitioners and theorists alike.
Energy Dissipation with Plug-and-Play Priors
In this paper we consider the combination of both approaches by projecting the outputs of a plug-and-play denoising network onto the cone of descent directions to a given energy.
Parametric Majorization for Data-Driven Energy Minimization Methods
Energy minimization methods are a classical tool in a multitude of computer vision applications.
Controlling Neural Networks via Energy Dissipation
The last decade has shown a tremendous success in solving various computer vision problems with the help of deep learning techniques.
Convolutional Simplex Projection Network (CSPN) for Weakly Supervised Semantic Segmentation
Weakly supervised semantic segmentation has been a subject of increased interest due to the scarcity of fully annotated images.
Are good local minima wide in sparse recovery?
The idea of compressed sensing is to exploit representations in suitable (overcomplete) dictionaries that allow to recover signals far beyond the Nyquist rate provided that they admit a sparse representation in the respective dictionary.
Lifting Layers: Analysis and Applications
A lifting layer increases the dimensionality of the input, naturally yields a linear spline when combined with a fully connected layer, and therefore closes the gap between low and high dimensional approximation problems.
Composite Optimization by Nonconvex Majorization-Minimization
A popular class of algorithms for solving such problems are majorization-minimization techniques which iteratively approximate the composite nonconvex function by a majorizing function that is easy to minimize.
DS*: Tighter Lifting-Free Convex Relaxations for Quadratic Matching Problems
In this work we study convex relaxations of quadratic optimisation problems over permutation matrices.
Proximal Backpropagation
Specifically, we show that backpropagation of a prediction error is equivalent to sequential gradient descent steps on a quadratic penalty energy, which comprises the network activations as variables of the optimization.
Learning Proximal Operators: Using Denoising Networks for Regularizing Inverse Imaging Problems
While variational methods have been among the most powerful tools for solving linear inverse problems in imaging, deep (convolutional) neural networks have recently taken the lead in many challenging benchmarks.
Multiframe Motion Coupling for Video Super Resolution
The idea of video super resolution is to use different view points of a single scene to enhance the overall resolution and quality.
Sublabel-Accurate Convex Relaxation of Vectorial Multilabel Energies
Convex relaxations of nonconvex multilabel problems have been demonstrated to produce superior (provably optimal or near-optimal) solutions to a variety of classical computer vision problems.
Sublabel-Accurate Relaxation of Nonconvex Energies
We propose a novel spatially continuous framework for convex relaxations based on functional lifting.
Learning Nonlinear Spectral Filters for Color Image Reconstruction
This paper presents the idea of learning optimal filters for color image reconstruction based on a novel concept of nonlinear spectral image decompositions recently proposed by Guy Gilboa.
Nonlinear Spectral Analysis via One-homogeneous Functionals - Overview and Future Prospects
We present in this paper the motivation and theory of nonlinear spectral representations, based on convex regularizing functionals.
Collaborative Total Variation: A General Framework for Vectorial TV Models
Even after over two decades, the total variation (TV) remains one of the most popular regularizations for image processing problems and has sparked a tremendous amount of research, particularly to move from scalar to vector-valued functions.
Point-wise Map Recovery and Refinement from Functional Correspondence
Since their introduction in the shape analysis community, functional maps have met with considerable success due to their ability to compactly represent dense correspondences between deformable shapes, with applications ranging from shape matching and image segmentation, to exploration of large shape collections.
Variational Depth from Focus Reconstruction
This paper deals with the problem of reconstructing a depth map from a sequence of differently focused images, also known as depth from focus or shape from focus.
The Primal-Dual Hybrid Gradient Method for Semiconvex Splittings
This paper deals with the analysis of a recent reformulation of the primal-dual hybrid gradient method [Zhu and Chan 2008, Pock, Cremers, Bischof and Chambolle 2009, Esser, Zhang and Chan 2010, Chambolle and Pock 2011], which allows to apply it to nonconvex regularizers as first proposed for truncated quadratic penalization in [Strekalovskiy and Cremers 2014].
