Adaptive relevance feedback for large-scale image retrieval

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.

We present a general variational framework for the training of freeform nonlinearities in layered computational architectures subject to some slope constraints. The regularization that we add to the traditional training loss penalizes the second-order tota ...

Neural Networks (NNs), renowned for their universal approximation capabilities, have proven well-suited for parametrizing nonlinear control policies and modeling complex processes from available data. However, several NN architectures are physics-agnostic, ...

Understanding the semantic connections between the increasingly online-based offered educational content is becoming more relevant for educational institutions. The fast adoption of AI-based techniques and their application in semantic search offers new po ...

Mapping the technology landscape is crucial for market actors to take informed investment decisions. However, given the large amount of data on the Web and its subsequent information overload, manually retrieving information is a seemingly ineffective and ...

Vision-Language Pre-training (VLP) has advanced the performance of many visionlanguage tasks, such as image-text retrieval, visual entailment, and visual reasoning. The pre-training mostly utilizes lexical databases and image queries in English. Previous w ...

Abstractive summarization has seen big improvements in recent years, mostly due to advances in neural language modeling, language model pretraining, and scaling models and datasets. While large language models generate summaries that are fluent, coherent, ...

This study presents a self-supervised Bayesian Neural Network (BNN) framework using air-borne Acoustic Emission (AE) to identify different Laser Powder Bed Fusion (LPBF) process regimes such as Lack of Fusion, conduction mode, and keyhole without ground-tr ...

Pulmonary nodules and masses are crucial imaging features in lung cancer screening that require careful management in clinical diagnosis. Despite the success of deep learning-based medical image segmentation, the robust performance on various sizes of lesi ...

Deep neural networks (DNNs) are increasingly proposed as models of human vision, bolstered by their impressive performance on image classification and object recognition tasks. Yet, the extent to which DNNs capture fundamental aspects of human vision such ...

Image-based retrieval in large Earth observation archives is difficult, because one needs to navigate across thousands of candidate matches only with the proposition image as a guide. By using text as a query language, the retrieval system gains in usabili ...

With the current exponential growth of video-based social networks, video retrieval using natural language is receiving ever-increasing attention. Most existing approaches tackle this task by extracting individual frame-level spatial features to represent ...

Information retrieval (IR) systems such as search engines are important for people to find what they need among the tremendous amount of data available in their organization or on the Internet. These IR systems enable users to search in a large data collec ...

Artificial intelligence has been an ultimate design goal since the inception of computers decades ago. Among the many attempts towards general artificial intelligence, modern machine learning successfully tackles many complex problems thanks to the progres ...

Deep neural networks (DNNs) have achieved great success in image classification and recognition compared to previous methods. However, recent works have reported that DNNs are very vulnerable to adversarial examples that are intentionally generated to misl ...

Large-scale models for learning fixed-dimensional cross-lingual sentence representations like LASER (Artetxe and Schwenk, 2019b) lead to significant improvement in performance on downstream tasks. However, further increases and modifications based on such ...

In the Digital Age, the analysis and exploration of unstructured document collections is of central importance to members of investigative professions, whether they might be scholars, journalists, paralegals, or analysts. In many of their domains, entities ...

Thanks to recent advancements in image processing and deep learning techniques, visual surface inspection in production lines has become an automated process as long as all the defects are visible in a single or a few images. However, it is often necessary ...

Flow-based generative models have become an important class of unsupervised learning approaches. In this work, we incorporate the key ideas of renormalization group (RG) and sparse prior distribution to design a hierarchical flow-based generative model, RG ...

Modern machine learning tools have shown promise in detecting symptoms of neurological disorders. However, current approaches typically train a unique classifier for each subject. This subject-specific training scheme requires long labeled recordings from ...

In the information age, the Web and the growing global connectivity drastically simplified our access to information. Learning and fact-checking from online resources is nowadays part of our daily routine. Studying the dynamic associated with online conten ...

Adaptive relevance feedback for large-scale image retrieval

Chat with Graph Search

Controlled learning of pointwise nonlinearities in neural-network-like architectures

Dependable learning and control through Neural ODEs

Retrieval-Augmented Generation for Finding Relevant Lectures from Quizzes in a Multilingual STEM Educational Environment

From scattered sources to comprehensive technology landscape : A recommendation-based retrieval approach

Stop Pre-Training: Adapt Visual-Language Models to Unseen Languages

Interpretable Representation Learning and Evaluation for Abstractive Summarization

Self-Supervised Bayesian representation learning of acoustic emissions from laser powder bed Fusion process for in-situ monitoring

Scale-Aware Test-Time Click Adaptation for Pulmonary Nodule and Mass Segmentation

Divergences in color perception between deep neural networks and humans

Knowledge-Aware Cross-Modal Text-Image Retrieval for Remote Sensing Images

Semantics-Aware Spatial-Temporal Binaries for Cross-Modal Video Retrieval

Graph Embedding for Retrieval

From Human-Designed Convolutional Neural Networks Towards Robust Neural Architecture Search

Natural-Looking Adversarial Examples From Freehand Sketches

Lightweight Cross-Lingual Sentence Representation Learning

ECCE: Entity-centric Corpus Exploration Using Contextual Implicit Networks

Defect segmentation for multi-illumination quality control systems

RG-Flow: a hierarchical and explainable flow model based on renormalization group and sparse prior

Unsupervised Domain Adaptation for Cross-Subject Few-Shot Neurological Symptom Detection

How We Use Wikipedia: Studying Readers' Behavior with Navigation Traces