Attribute Prediction as Multiple Instance Learning

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.

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 ...

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 ...

Neurodegenerative and neuroinflammatory disorders often involve complex pathophysiological mechanisms that are â to this date â only partially understood. A more comprehensive understanding of those microstructural processes and their characterization ...

Computing servers have played a key role in developing and processing emerging compute-intensive applications in recent years. Consolidating multiple virtual machines (VMs) inside one server to run various applications introduces severe competence for limi ...

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 ...

Methods based on Contrastive Language-Image Pre-training (CLIP) are nowadays extensively used in support of vision-and-language tasks involving remote sensing data, such as cross-modal retrieval. The adaptation of CLIP to this specific domain has relied on ...

Tightly-coupled sensor orientation, i.e. the simultaneous processing of temporal (GNSS and raw inertial) and spatial (image and lidar) constraints in a common adjustment, has demonstrated significant improvement in the quality of attitude determination wit ...

Federated Learning (FL) has gained considerable attention recently, as it allows clients to cooperatively train a global machine learning model without sharing raw data. However, its performance can be compromised due to the high heterogeneity in clients' ...

While understanding the shear strength of stone masonry structures is important for the design and the mainte- nance, we still lack computational tools for predicting the strength as a function of the stone layout. Here we implement an end-to-end image bas ...

Test time augmentation has been shown to be an effective approach to combat domain shifts in deep learning. Despite their promising performance levels, the interpretability of the underlying used models is however low. Saliency maps have been widely used i ...

We address the problem of segmenting anomalies and unusual obstacles in road scenes for the purpose of self-driving safety. The objects in question are not present in the common training sets as it is not feasible to collect and annotate examples for every ...

In the context of automatic visual inspection of infrastructures by drones, Deep Learning (DL) models are used to automatically process images for fault diagnostics. While explainable Artificial Intelligence (AI) algorithms can provide explanations to asse ...

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 ...

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 ...

Dense image-based prediction methods have advanced tremendously in recent years. Their remarkable development has been possible due to the ample availability of real-world imagery. While these methods work well on photographs, their abilities do not genera ...

Robustness of medical image classification models is limited by its exposure to the candidate disease classes. Generalized zero shot learning (GZSL) aims at correctly predicting seen and unseen classes and most current GZSL approaches have focused on the s ...

Over the years, clinical institutes accumulated large amounts of digital slides from resected tissue specimens. These digital images, called whole slide images (WSIs), are high-resolution tissue snapshots that depict the complex interaction of cells at the ...

Recent advances in image compression have made it both possible and desirable for image quality to approach the visually lossless range. However, the most commonly used subjective visual quality assessment protocols, e.g. those reported in ITU-T Rec. BT.50 ...

In this paper, we develop a MultiTask Learning (MTL) model to achieve dense predictions for comic panels to, in turn, facilitate the transfer of comics from one publication channel to another by assisting authors in the task of reconfiguring their narrativ ...

Ultrafast ultrasound imaging, characterized by high frame rates, generates low-quality images. Convolutional neural networks (CNNs) have demonstrated great potential to enhance image quality without compromising the frame rate. However, CNNs have been most ...

Attribute Prediction as Multiple Instance Learning

Chat with Graph Search

Aggregating Spatial and Photometric Context for Photometric Stereo

Incorporating Projective Geometry into Deep Learning

Development and clinical validation of computational imaging biomarkers for neurodegenerative diseases

CloudProphet: A Machine Learning-Based Performance Prediction for Public Clouds

Fast and Future: Towards Efficient Forecasting in Video Semantic Segmentation

Multilingual Vision-Language Pre-training for the Remote Sensing Domain

Airborne sensor fusion: Expected accuracy and behavior of a concurrent adjustment

Rethinking Personalized Client Collaboration in Federated Learning

Micro modeling of irregular stone masonry walls using mathematical programming

SAGTTA: SALIENCY GUIDED TEST TIME AUGMENTATION FOR MEDICAL IMAGE SEGMENTATION ACROSS VENDOR DOMAIN SHIFT

Detecting Anomalies and Obstacles in Road Scenes

Exploiting Explanations to Detect Misclassifications of Deep Learning Models in Power Grid Visual Inspection

Text as a Richer Source of Supervision in Semantic Segmentation Tasks

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

Dense Image-based Predictions for Comics Analysis

Class Specific Feature Disentanglement and Text Embeddings for Multi-label Generalized Zero Shot CXR Classification

Self-Supervised Learning for Patient Stratification and Survival Analysis in Computational Pathology: An Application to Colorectal Cancer

On the assessment of high-quality images: advances on the JPEG AIC-3 activity

Dense Multitask Learning to Reconfigure Comics

A KL Divergence-Based Loss for In Vivo Ultrafast Ultrasound Image Enhancement with Deep Learning