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.
Few-shot learning aims to correctly recognize query samples from unseen classes given a limited number of support samples, often by relying on global embeddings of images. In this paper, we propose to equip the backbone network with an attention agent, whi ...
Serial crystallography at X-ray free-electron lasers (XFELs) permits the determination of radiation-damage free static as well as time-resolved protein structures at room temperature. Efficient sample delivery is a key factor for such experiments. Here, we ...
Background: Large-scale proteomic studies have to deal with unwanted variability, especially when samples originate from different centers and multiple analytical batches are needed. Such variability is typically added throughout all the steps of a clinica ...
Time series of hydrochemical parameters support the investigation of dominant karst hydrological processes and conceptual model structures. Nevertheless, high costs for sample collection and analyses cause hydrochemical data to be rarely available at a suf ...
Mars Polar Ice caps have been known ever since they were first observed by Cassini. Robotic exploration mis- sions, starting with Mariner 9, have confirmed that they are composed of water ice. During later missions, instruments such as Mars Global Surveyor ...
In this paper, a novel SAR ADC architecture enabling very high speed operation is presented. Based on a hybrid capacitive DAC-threshold configuring scheme, the proposed architecture performs conversions in two-stages, similarly to pipelined ADCs. An additi ...
The work presented in this dissertation lies in the domains of image classification, object detection, and machine learning. Whether it is training image classifiers or object detectors, the learning phase consists in finding an optimal boundary between po ...
The work presented in this dissertation lies in the domains of image classification, object detection, and machine learning. Whether it is training image classifiers or object detectors, the learning phase consists in finding an optimal boundary between po ...
Visual Question Answering is a new task that can facilitate the extraction of information from images through textual queries: it aims at answering an open-ended question formulated in natural language about a given image. In this work, we introduce a new ...
The historical development of ice nucleating particle concentrations (NINP) is still unknown. Here, we present for the first time NINP from the past 500 years at two Arctic sites derived from ice core samples. The samples originate from the EUROCORE ice co ...
