Cross-resolution Face Recognition via Identity-Preserving Network and Knowledge Distillation

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.

Recent progress in computer vision has been driven by a simple yet transformative observation: the potential of 30-year-old neural networks can be unlocked by massively scaling their parameters and the amount of human-labeled training data. This breakthrou ...

Low-light photography produces images with low signal-to-noise ratios due to limited photons. In such conditions, common approximations like the Gaussian noise model fall short, and many denoising techniques fail to remove noise effectively. Although deep- ...

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 ...

Semi-supervised semantic segmentation methods leverage unlabeled data by pseudo-labeling them. Thus the success of these methods hinges on the reliability of the pseudo-labels. Existing methods mostly choose high-confidence pixels in an effort to avoid err ...

Data augmentation is vital in deep learning for enhancing model robustness by artificially expanding training datasets. However, advanced methods like CutMix blend images and assign labels based on pixel ratios, often introducing label noise by neglecting ...

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 ...

Purpose: Although clinical 7T MRI offers various advantages compared to lower field strengths, achieving spatially uniform flip angle distributions remains a challenge. Sampling Perfection with Application optimized Contrast using different flip angle Evol ...

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 ...

Recently, the R2D2 paradigm, standing for ‘Residual-to-Residual DNN series for high-Dynamic-range imaging’, was introduced for image formation in Radio Interferometry (RI) as a learned version of the traditional algorithm CLEAN. The first incarnations of R ...

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 ...

Deep learning has shown remarkable potential for industrial applications, particularly in predictive maintenance and condition monitoring. A key challenge in this domain is prognostics, specifically predicting the Remaining Useful Life (RUL) of assets - a ...

The field of biometrics, and especially face recognition, has seen a wide-spread adoption the last few years, from access control on personal devices such as phones and laptops, to automated border controls such as in airports. The stakes are increasingly ...

Decentralized learning (DL) is an emerging approach that enables nodes to collaboratively train a machine learning model without sharing raw data. In many application domains, such as healthcare, this approach faces challenges due to the high level of hete ...

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 ...

The proliferation of microscopy methods for live-cell imaging offers many new possibilities for users but can also be challenging to navigate. The prevailing challenge in live-cell fluorescence microscopy is capturing intra-cellular dynamics while preservi ...

The evolution of airborne mapping witnesses the introduction of hybrid lidar-camera systems to enhance data collection, i.e. to obtain simultaneously high-density point-cloud and texture. Yet, the common adjustment of both optical data streams is a nontriv ...

The visualization and manipulation of proteins in live cells are critical for studying complex biological processes. Self-labeling proteins do so by enabling the specific and covalent attachment of synthetic probes, offering unprecedented flexibility in th ...

Effective Prognostics and Health Management (PHM) relies on accurate prediction of the Remaining Useful Life (RUL). Data-driven RUL prediction techniques rely heavily on the representativeness of the available time-to-failure trajectories. Therefore, these ...

Proteins are the molecular machines of life, driving essential biological processes such as enzymatic catalysis, cellular signaling, and immune responses. The ability to design entirely new proteins with desired structures and functions has immense implica ...

The current machine learning paradigm relies on continuous representations and fixed neural network architectures to approximate environmental structures, leading to challenges with continual learning, internal structure design, and goal-directed behavior ...

Cross-resolution Face Recognition via Identity-Preserving Network and Knowledge Distillation

Chat with Graph Search

Exploiting Representation Similarities in Self-Supervised Learning for Vision Tasks

Dark Noise Diffusion: Noise Synthesis for Low-Light Image Denoising

Towards Trustworthy Deep Learning for Image Reconstruction

Weighting Pseudo-labels via High-Activation Feature Index Similarity and Object Detection for Semi-supervised Segmentation

SaliencyMix plus : Noise-Minimized Image Mixing Method With Saliency Map in Data Augmentation

Advancing Self-Supervised Deep Learning for 3D Scene Understanding

Individually optimized dynamic parallel transmit pulses for 3D high‐resolution SPACE imaging at 7T

Enabling Uncertainty Estimation in Iterative Neural Networks

S-R2D2: a spherical extension of the R2D2 deep neural network series paradigm for wide-field radio-interferometric imaging

Fast and Future: Towards Efficient Forecasting in Video Semantic Segmentation

Overcoming Distribution Shifts and Imbalance Challenges in Representation Learning for Deep Regression Models

Performing and Detecting Backdoor Attacks on Face Recognition Algorithms

Fair Decentralized Learning

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

Live-cell imaging powered by computation

On the Perspectives of Image-to-Lidar Constraints in Dynamic Network Optimisation

Exploiting Covalent Chemical Labeling with Self-Labeling Proteins

Domain adaptation via alignment of operation profile for Remaining Useful Lifetime prediction

Computational design of complex protein folds and soluble analogs of membrane proteins

Modelleyen: Continual Learning and Planning via Structured Modelling of Environment Dynamics