On the Relevance of Sparsity for Image Classification

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.

Faithful human performance capture and free-view rendering from sparse RGB observations is a long-standing problem in Vision and Graphics. The main challenges are the lack of observations and the inherent ambiguities of the setting, e.g. occlusions and dep ...

Photometric stereo, a computer vision technique for estimating the 3D shape of objects through images captured under varying illumination conditions, has been a topic of research for nearly four decades. In its general formulation, photometric stereo is an ...

Turning pass-through network architectures into iterative ones, which use their own output as input, is a well-known approach for boosting performance. In this paper, we argue that such architectures offer an additional benefit: The convergence rate of the ...

Deep learning has revolutionized the field of computer vision, a success largely attributable to the growing size of models, datasets, and computational power. Simultaneously, a critical pain point arises as several computer vision applications are deploye ...

Recent advancements in deep learning have revolutionized 3D computer vision, enabling the extraction of intricate 3D information from 2D images and video sequences. This thesis explores the application of deep learning in three crucial challenges of 3D com ...

Solid-State Transformers with Input-Series/Output-Parallel configuration offer a convenient solution for AC/DC conversion due to their scalability and modularity. In this configuration, each module experiences a second-order harmonic ripple caused by local ...

Deep learning has emerged as a promising avenue for automatic mapping, demonstrating high efficacy in land cover categorization through various semantic segmentation models. Nonetheless, the practical deployment of these models encounters important challen ...

Digital twins are virtual models of physical objects or systems that enable real-time monitoring and analysis. In the ﬁeld of stone masonry buildings, digital twins can be used to assess damage, predict maintenance needs, and opti- mize building performanc ...

The remarkable ability of deep learning (DL) models to approximate high-dimensional functions from samples has sparked a revolution across numerous scientific and industrial domains that cannot be overemphasized. In sensitive applications, the good perform ...

In this thesis we explore the applications of projective geometry, a mathematical theory of the relation between 3D scenes and their 2D images, in modern learning-based computer vision systems. This is an interesting research question which contradicts the ...

The success of the Neural Radiance Fields (NeRF) in novel view synthesis has inspired researchers to propose neural implicit scene reconstruction. However, most existing neural implicit reconstruction methods optimize perscene parameters and therefore lack ...

Monitoring forests, in particular their response to climate and land use change, requires studying long time scales. While efficient deep learning methods have been developed to process short time series of satellite imagery, leveraging long time series of ...

We formulate computed-tomography reconstruction as a continuous-domain optimization problem with Hessian total variation (HTV) as the regularizer. HTV is a sparsity-promoting regularizer that favors continuous and piecewise-linear functions with few affine ...

In this paper, we present EdgeFace - a lightweight and efficient face recognition network inspired by the hybrid architecture of EdgeNeXt. By effectively combining the strengths of both CNN and Transformer models, and a low rank linear layer, EdgeFace achi ...

This paper introduces TACOSS a text-image alignment approach that allows explainable land cover semantic segmentation by directly integrating semantic concepts encoded from texts. TACOSS combines convolutional neural networks for visual feature extraction ...

A closed-loop neuromodulation system, including an electrode array that is implantable to a brain of a subject, analog front-end device (AFD) for selectively selecting and reading a plurality of channels from electrode array, a finite impulse response (FIR ...

The recent developments of deep learning cover a wide variety of tasks such as image classification, text translation, playing go, and folding proteins. All these successful methods depend on a gradient-based learning algorithm to train a model on massive ...

The Joint Photographic Experts Group (JPEG) AI learning-based image coding system is an ongoing joint standardization effort between International Organization for Standardization (ISO), International Electrotechnical Commission (IEC), and International Te ...

Single Domain Generalization (SDG) tackles the problem of training a model on a single source domain so that it generalizes to any unseen target domain. While this has been well studied for image classification, the literature on SDG object detection remai ...

Artificial intelligence, particularly the subfield of machine learning, has seen a paradigm shift towards data-driven models that learn from and adapt to data. This has resulted in unprecedented advancements in various domains such as natural language proc ...

On the Relevance of Sparsity for Image Classification

Chat with Graph Search

MetaCap: Meta-learning Priors from Multi-view Imagery for Sparse-View Human Performance Capture and Rendering

Aggregating Spatial and Photometric Context for Photometric Stereo

Enabling Uncertainty Estimation in Iterative Neural Networks

Fast and Future: Towards Efficient Forecasting in Video Semantic Segmentation

Advancing Self-Supervised Deep Learning for 3D Scene Understanding

Stability Analysis of Input-Series/Output-Parallel Solid-State Transformers Equipped with Second-Order Harmonic Active Power Filters

Land Cover Mapping From Multiple Complementary Experts Under Heavy Class Imbalance

Digital Twins of Stone Masonry Buildings for Damage Assessment

Towards Trustworthy Deep Learning for Image Reconstruction

Incorporating Projective Geometry into Deep Learning

VolRecon: Volume Rendering of Signed Ray Distance Functions for Generalizable Multi-View Reconstruction

Multi-temporal forest monitoring in the Swiss Alps with knowledge-guided deep learning

A Continuous-Domain Solution for Computed Tomography with Hessian Total-Variation Regularization

EdgeFace: Efficient Face Recognition Model for Edge Devices

Text as a Richer Source of Supervision in Semantic Segmentation Tasks

A multichannel versatile brain activity classification and closed loop neuromodulation system, device and method using a highly multiplexed mixed-signal front-end

Transformer Models for Vision

The JPEG AI Standard: Providing Efficient Human and Machine Visual Data Consumption

CLIP the Gap: A Single Domain Generalization Approach for Object Detection

Breaking the Curse of Dimensionality in Deep Neural Networks by Learning Invariant Representations