Beyond the Pixel-Wise Loss for Topology-Aware Delineation

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Current transformer-based skeletal action recognition models tend to focus on a limited set of joints and low-level motion patterns to predict action classes. This results in significant performance degradation under small skeleton perturbations or changin ...

We present a statistical framework to benchmark the performance of reconstruction algorithms for linear inverse problems, in particular, neural-network-based methods that require large quantities of training data. We generate synthetic signals as realizati ...

One of the most classical results in high-dimensional learning theory provides a closed-form expression for the generalisation error of binary classification with a single-layer teacher-student perceptron on i.i.d. Gaussian inputs. Both Bayes-optimal (BO) ...

We consider the problem of compressing an information source when a correlated one is available as side information only at the decoder side, which is a special case of the distributed source coding problem in information theory. In particular, we consider ...

Using Bayes's theorem, we derive a unit-wise recurrence as well as a backward recursion similar to the forward-backward algorithm. The resulting Bayesian recurrent units can be integrated as recurrent neural networks within deep learning frameworks, while ...

Vision sensor networks and video cameras find widespread usage in several applications that rely on effective representation of scenes or analysis of 3D information. These systems usually acquire multiple images of the same 3D scene from different viewpoin ...

Convolutional neural networks perform a local and translationally-invariant treatment of the data: quantifying which of these two aspects is central to their success remains a challenge. We study this problem within a teacher-student framework for kernel r ...

The field of computational topology has developed many powerful tools to describe the shape of data, offering an alternative point of view from classical statistics. This results in a variety of complex structures that are not always directly amenable for ...

This paper proposes a joint reconstruction algorithm for compressed correlated images that are given under the form of linear measurements. We consider the particular problem where one image is selected as the reference image and it is used as the side inf ...

This paper proposes a joint reconstruction algorithm for compressed correlated images that are given under the form of linear measurements. We first propose a geometry based model in order to describe the correlation between visual information in pairs of ...

The increasing prevalence of personal devices motivates the design of algorithms that can leverage their computing power, together with the data they generate, in order to build privacy-preserving and effective machine learning models. However, traditional ...

In this work we introduce a manifold learning-based method for uncertainty quantification (UQ) in systems describing complex spatiotemporal processes. Our first objective is to identify the embedding of a set of high-dimensional data representing quantitie ...

This paper presents a highly flexible video coding scheme (MP3D), based on the use of a redundant 3-D spatio-temporal dictionary of functions. Directionality and anisotropic scaling are key ingredients to the spatial components, that form a rich collection ...

This paper presents a progressive coding scheme for 3-D objects, based on overcomplete signal expansions on the 2-D sphere. Due to increased freedom in the basis construction, redundant expansions have shown interesting approximation properties in the deco ...

Digitization and preservation of large heritage induce high maintenance costs to keep up with the technical standards and ensure sustainable access. Creating impactful usage is instrumental to justify the resources for long-term preservation. The Museum fü ...

Learning in the brain is poorly understood and learning rules that respect biological constraints, yet yield deep hierarchical representations, are still unknown. Here, we propose a learning rule that takes inspiration from neuroscience and recent advances ...

In this paper, we propose a multi-fidelity approach for parameter estimation problems based on Physics-Informed Neural Networks (PINNs). The proposed methods apply to models expressed by linear or nonlinear differential equations, whose parameters need to ...

Deep learning has been immensely successful at a variety of tasks, ranging from classification to artificial intelligence. Learning corresponds to fitting training data, which is implemented by descending a very high-dimensional loss function. Understandin ...

Transportation systems often rely on understanding the flow of vehicles or pedestrian. From traffic monitoring at the city scale, to commuters in train terminals, recent progress in sensing technology make it possible to use cameras to better understand th ...

Deep unfolding is a method of growing popularity that fuses iterative optimization algorithms with tools from neural networks to efficiently solve a range of tasks in machine learning, signal and image processing, and communication systems. This survey sum ...

Beyond the Pixel-Wise Loss for Topology-Aware Delineation

Chat with Graph Search

MaskCLR: Attention-Guided Contrastive Learning for Robust Action Representation Learning

A Statistical Framework to Investigate the Optimality of Signal-Reconstruction Methods

Learning curves for the multi-class teacher-student perceptron

Neural Distributed Image Compression with Cross-Attention Feature Alignment

Bayesian Recurrent Units and the Forward-Backward Algorithm

Distributed Compressed Representation of Correlated Image Sets

Locality defeats the curse of dimensionality in convolutional teacher-student scenarios*

Reduced representations of complexes, signals, and multifiltrations

Image Reconstruction from Compressed Linear Measurements with Side Information

Joint reconstruction of correlated images from compressed linear measurements

Democratizing Machine Learning

Manifold Learning-Based Polynomial Chaos Expansions For High-Dimensional Surrogate Models

Flexible Motion-Adaptive Video Coding with Redundant Expansions

Progressive Coding of 3-D Objects Based on Overcomplete Decompositions

Automatic Content Curation of Visual Heritage

Local plasticity rules can learn deep representations using self-supervised contrastive predictions

Numerical Analysis - A physics-informed multi-fidelity approach for the estimation of differential equations parameters in low-data or large-noise regimes

Jamming transition as a paradigm to understand the loss landscape of deep neural networks

Deep Visual Re-Identification with Confidence

Deep Unfolding for Communications Systems: A Survey and Some New Directions