Test-Time Adaptation for Super-Resolution: You Only Need to Overfit on a Few More Images

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.

The projection of fifth-generation (5G) fractal antennas and their advantageous geometry are examined. The fact that fractal-shaped antennas based on Koch Snowflake geometry are suitable for higher frequencies was shown above all. By the instrumentality of ...

With the increasing dominance of SSDs for local storage, today's network mounted virtual disks can no longer offer competitive performance. We propose a Log-Structured Virtual Disk (LSVD) that couples log-structured approaches at both the cache and storage ...

We relate discrepancy theory with the classic scheduling problems of minimizing max flow time and total flow time on unrelated machines. Specifically, we give a general reduction that allows us to transfer discrepancy bounds in the prefix Beck-Fiala (bound ...

We consider the problem of enhancing user privacy in common data analysis and machine learning development tasks, such as data annotation and inspection, by substituting the real data with samples from a generative adversarial network. We propose employing ...

In this paper, we propose a novel semi-supervised active salient object detection (SOD) method that actively acquires a small subset of the most discriminative and representative samples for labeling. Two main contributions have been made to prevent the me ...

Background A variety of imaging methods are available to obtain kinematic data at an interface, with a widely varying range of spatial and temporal resolution. These methods require a trade-off between imaging rate and resolution. Objective A deep learning ...

Several groups developed in the last years augmented and virtual reality (AR/VR) software to visualize 3D molecules, most rather static, limited in content, and requiring software installs, some even requiring expensive hardware. We launched in 2020 molecu ...

Digital images enable quantitative analysis of material properties at micro and macro length scales, but choosing an appropriate resolution when acquiring the image is challenging. A high resolution means longer image acquisition and larger data requiremen ...

We derive an upper bound on the reliability function of mismatched decoding for zero-rate codes. The bound is based on a result by Komlos that shows the existence of a subcode with certain symmetry properties. The bound is shown to coincide with the expurg ...

Despite their irresistible success, deep learning algorithms still heavily rely on annotated data, and unsupervised settings pose many challenges, such as finding the right inductive bias in diverse scenarios. In this paper, we propose an object-centric mo ...

We present a structure preserving discretization of the fundamental spacetime geometric structures of fluid mechanics in the Lagrangian description in 2D and 3D. Based on this, multisymplectic variational integrators are developed for barotropic and incomp ...

Spatial count data models are used to explain and predict the frequency of phenomena such as traffic accidents in geographically distinct entities such as census tracts or road segments. These models are typically estimated using Bayesian Markov chain Mont ...

Fuzzing is a testing technique to discover unknown vulnerabilities in software. When applying fuzzing to libraries, the core idea of supplying random input remains unchanged, yet it is non-trivial to achieve good code coverage. Libraries cannot run as stan ...

Sharing photos online has become an extremely popular activity, raising a wide concern on privacy issues related to the shared content. ProShare, a photo-sharing solution developed by Multimedia Signal Processing Group of EPFL addresses some of these priva ...

Random Feature (RF) models are used as efficient parametric approximations of kernel methods. We investigate, by means of random matrix theory, the connection between Gaussian RF models and Kernel Ridge Regression (KRR). For a Gaussian RF model with P feat ...

Despite significant progress toward super resolving more realistic images by deeper convolutional neural networks (CNNs), reconstructing fine and natural textures still remains a challenging problem. Recent works on single image super resolution (SISR) are ...

We present Mmkg, a collection of three knowledge graphs that contain both numerical features and (links to) images for all entities as well as entity alignments between pairs of KGs. Therefore, multi-relational link prediction and entity matching communiti ...

We present LANCET, a self-correcting tool designed to measure the open-loop tail latency of µs-scale datacenter applications with high fan-in connection patterns. LANCET is self-correcting as it relies on online statistical tests to determine situations in ...

With the recent development of fluorescent probes and new high-resolution microscopes, biological imaging has entered a new era and is presently having a profound impact on the way research is being conducted in the life sciences. Biologists have come to d ...

Test-Time Adaptation for Super-Resolution: You Only Need to Overfit on a Few More Images

Chat with Graph Search

Fifth-generation fractal antenna design based on the Koch Snowflake geometry. A fractal theory application

Beating the I/O Bottleneck: A Case for Log-Structured Virtual Disks

Flow Time Scheduling and Prefix Beck-Fiala

Generating Higher-Fidelity Synthetic Datasets with Privacy Guarantees

Semi-supervised Active Salient Object Detection

High Resolution Interferometric Imaging of Liquid-Solid Interfaces with HOTNNET

Online tools to easily build virtual molecular models for display in augmented and virtual reality on the web

The Impact of Changes in Resolution on the Persistent Homology of Images

Zero-rate Reliability Function for Mismatched Decoding

Self-Supervision By Prediction For Object Discovery In Videos

Soft Bionic Sensors and Actuators

Multisymplectic Variational Integrators for Fluid Models with Constraints

Fast Bayesian estimation of spatial count data models

FuzzGen: Automatic Fuzzer Generation

Privacy-preserving photo sharing based on blockchain

Implicit Regularization of Random Feature Models

Benefiting from Multitask Learning to Improve Single Image Super-Resolution

MMKG: Multi-modal Knowledge Graphs

Lancet: A self-correcting Latency Measuring Tool

The Colored Revolution of Bioimaging