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

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.

This study presents an augmented hybrid approach for improving the diagnosis of malignant skin lesions by combining convolutional neural network (CNN) predictions with selective human interventions based on prediction confidence. The algorithm retains high ...

Self-supervised pretrained models exhibit competitive performance in automatic speech recognition (ASR) on finetuning, even with limited in-domain supervised data. However, popular pretrained models are not suitable for streaming ASR because they are train ...

Sonic Human-Robot Interaction aims at equipping robots with the ability to convey emotions and intentions via sounds. Such sounds are typically handcrafted by human experts, which results in expensive, small sound sets with limited expressivity. To overcom ...

Automatic speech recognition (ASR) systems are well known to perform poorly on dysarthric speech. Previous works have addressed this by speaking rate modification to reduce the mismatch with typical speech. Unfortunately, these approaches rely on transcrib ...

Faithful human performance capture and free-view rendering from sparse RGB observations is a long-standing problem in Vision and Graphics. The main challenges are the lack of observations and the inherent ambiguities of the setting, e.g. occlusions and dep ...

Cancer is among the leading causes of death worldwide, and as knowledge of the disease continues to grow there is an increasing interest towards precision medicine: more specifically towards the theranostics field, i.e the development of targeted molecular ...

Machine learning (ML) enables artificial intelligent (AI) agents to learn autonomously from data obtained from their environment to perform tasks. Modern ML systems have proven to be extremely effective, reaching or even exceeding human intelligence. Altho ...

Whether a document is of historical or contemporary significance, typography plays a crucial role in its composition. From the early days of modern printing, typographic techniques have evolved and transformed, resulting in changes to the features of typog ...

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 ...

The recent developments of deep learning cover a wide variety of tasks such as image classification, text translation, playing go, and folding proteins. All these successful methods depend on a gradient-based learning algorithm to train a model on massive ...

Text-to-image models, such as Stable Diffusion, can generate high-quality images from simple textual prompts. With methods such as Textual Inversion, it is possible to expand the vocabulary of these models with additional concepts, by learning the vocabula ...

Informative sample selection in an active learning (AL) setting helps a machine learning system attain optimum performance with minimum labeled samples, thus reducing annotation costs and boosting performance of computer-aided diagnosis systems in the pres ...

Cell segmentation is a critical step for quantitative single-cell analysis in microscopy images. Existing cell segmentation methods are often tailored to specific modalities or require manual interventions to specify hyper-parameters in different experimen ...

We propose a methodology to monitor the progressive saturation of a non-translucent unidirectional carbon fabric stack through its thickness by means of X-ray radiography and extract the dynamic saturation curves using image analysis. Four constant flow ra ...

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 ...

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 ...

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 ...

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 ...

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, ...

The ability to reason, plan and solve highly abstract problems is a hallmark of human intelligence. Recent advancements in artificial intelligence, propelled by deep neural networks, have revolutionized disciplines like computer vision and natural language ...

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

Chat with Graph Search

Enhancing skin lesion classification: a CNN approach with human baseline comparison

XLSR-Transducer: Streaming ASR for Self-Supervised Pretrained Models

Automated Generation of Emotion-Conveying Sounds for Robots

Unsupervised Rhythm and Voice Conversion of Dysarthric to Healthy Speech for ASR

MetaCap: Meta-learning Priors from Multi-view Imagery for Sparse-View Human Performance Capture and Rendering

Functionalization of harmonic nanoparticles for drug release and multimodal imaging applications

Few-shot Learning for Efficient and Effective Machine Learning Model Adaptation

Toward Automatic Typography Analysis: Serif Classification and Font Similarities

Aggregating Spatial and Photometric Context for Photometric Stereo

Transformer Models for Vision

VETIM: Expanding the Vocabulary of Text-to-Image Models only with Text

GANDALF: Graph-based transformer and Data Augmentation Active Learning Framework with interpretable features for multi-label chest Xray classification

The multimodality cell segmentation challenge: toward universal solutions

Measurement and modelling of dynamic fluid saturation in carbon reinforcements

Development and clinical validation of computational imaging biomarkers for neurodegenerative diseases

Text as a Richer Source of Supervision in Semantic Segmentation Tasks

Advancing Self-Supervised Deep Learning for 3D Scene Understanding

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

Interpretable Representation Learning and Evaluation for Abstractive Summarization

Infusing structured knowledge priors in neural models for sample-efficient symbolic reasoning