8 citations · 59 across the 37 of their papers we have counts for
13 papers · 1 filter
RAMP: Robust Adaptive Mixed-Precision Quantization for Edge CPU Vision Models
David Población-Criado, Dario Garcia-Gasulla, Eduardo Quinones
Deploying deep learning models on edge CPUs is bottlenecked by computational and memory constraints. Mixed-precision quantization promises to reduce inference latency while preserv…
Aloe-Vision: Robust Vision-Language Models for Healthcare
Jaume Guasch-Martí, Enrique Lopez-Cuena, Martín Suárez-Fernández +3
Large Vision-Language Models (LVLMs) specialized in healthcare are emerging as a promising research direction due to their potential impact in clinical and biomedical applications.…
Language Models Can Explain Visual Features via Steering
Javier Ferrando, Enrique Lopez-Cuena, Pablo Agustin Martin-Torres +3
Sparse Autoencoders uncover thousands of features in vision models, yet explaining these features without requiring human intervention remains an open challenge. While previous wor…
Data Augmentation with Diffusion Models for Colon Polyp Localization on the Low Data Regime: How much real data is enough?
Adrian Tormos, Blanca Llauradó, Fernando Núñez +3
The scarcity of data in medical domains hinders the performance of Deep Learning models. Data augmentation techniques can alleviate that problem, but they usually rely on functiona…
Present and Future Generalization of Synthetic Image Detectors
Pablo Bernabeu-Perez, Enrique Lopez-Cuena, Dario Garcia-Gasulla
The continued release of increasingly realistic image generation models creates a demand for synthetic image detectors. To build effective detectors we must first understand how fa…
Padding Aware Neurons
Dario Garcia-Gasulla, Victor Gimenez-Abalos, Pablo Martin-Torres
Convolutional layers are a fundamental component of most image-related models. These layers often implement by default a static padding policy (\eg zero padding), to control the sc…
Exploring the Role of Explainability in AI-Assisted Embryo Selection
Lucia Urcelay, Daniel Hinjos, Pablo A. Martin-Torres +5
In Vitro Fertilization is among the most widespread treatments for infertility. One of its main challenges is the evaluation and selection of embryo for implantation, a process wit…
When & How to Transfer with Transfer Learning
Adrian Tormos, Dario Garcia-Gasulla, Victor Gimenez-Abalos +1
In deep learning, transfer learning (TL) has become the de facto approach when dealing with image related tasks. Visual features learnt for one task have been shown to be reusable…
The MAMe Dataset: On the relevance of High Resolution and Variable Shape image properties
Ferran Parés, Anna Arias-Duart, Dario Garcia-Gasulla +4
In the image classification task, the most common approach is to resize all images in a dataset to a unique shape, while reducing their precision to a size which facilitates experi…
Obstruction level detection of sewer videos using convolutional neural networks
Mario A. Gutierrez-Mondragon, Dario Garcia-Gasulla, Sergio Alvarez-Napagao +2
Worldwide, sewer networks are designed to transport wastewater to a centralized treatment plant to be treated and returned to the environment. This process is critical for the curr…
MetH: A family of high-resolution and variable-shape image challenges
Ferran Parés, Dario Garcia-Gasulla, Harald Servat +2
High-resolution and variable-shape images have not yet been properly addressed by the AI community. The approach of down-sampling data often used with convolutional neural networks…
Full-Network Embedding in a Multimodal Embedding Pipeline
Armand Vilalta, Dario Garcia-Gasulla, Ferran Parés +4
The current state-of-the-art for image annotation and image retrieval tasks is obtained through deep neural networks, which combine an image representation and a text representatio…
A Visual Embedding for the Unsupervised Extraction of Abstract Semantics
D. Garcia-Gasulla, J. Béjar, U. Cortés +4
Vector-space word representations obtained from neural network models have been shown to enable semantic operations based on vector arithmetic. In this paper, we explore the existe…