Prompt–RSVQA: Prompting visual context to a language model for Remote Sensing Visual Question Answering

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.

Analysis of single-cell datasets generated from diverse organisms offers unprecedented opportunities to unravel fundamental evolutionary processes of conservation and diversification of cell types. However, interspecies genomic differences limit the joint ...

Generative language models (LMs) have become omnipresent across data science. For a wide variety of tasks, inputs can be phrased as natural language prompts for an LM, from whose output the solution can then be extracted. LM performance has consistently be ...

In this thesis, we study two closely related directions: robustness and generalization in modern deep learning. Deep learning models based on empirical risk minimization are known to be often non-robust to small, worst-case perturbations known as adversari ...

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 ...

We are motivated primarily by the adaptation of text-to-speech synthesis models; however we argue that more generic parameter-efficient fine-tuning (PEFT) is an appropriate framework to do such adaptation. Nevertheless, catastrophic forgetting remains an i ...

Catastrophic overfitting (CO) in single-step adversarial training (AT) results in abrupt drops in the adversarial test accuracy (even down to 0%). For models trained with multi-step AT, it has been observed that the loss function behaves locally linearly w ...

Recent years have seen remarkable advancements in saliency estimation methods, mainly due to deep learning models leveraging the widespread availability of real-world images. However, saliency is profoundly shaped by the intricacies of the human visual att ...

Modern neuroscience research is generating increasingly large datasets, from recording thousands of neurons over long timescales to behavioral recordings of animals spanning weeks, months, or even years. Despite a great variety in recording setups and expe ...

Viewers of 360-degree videos are provided with both visual modality to characterize their surrounding views and audio modality to indicate the sound direction. Though both modalities are important for saliency prediction, little work has been done by joint ...

Understanding visual complexity of urban environments may improve urban design strategies and limit visual pollution due to advertising, road signage, telecommunication systems and machinery. This paper aims at quantifying visual complexity specifically in ...

Decisions about a current visual stimulus are systematically biased by recently encountered stimuli, a phenomenon known as serial dependence. In human vision, for instance, we tend to report the features of current images as more similar â i.e., an attra ...

Neural decoding of the visual system is a subject of research interest, both to understand how the visual system works and to be able to use this knowledge in areas, such as computer vision or brain-computer interfaces. Spike-based decoding is often used, ...

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 ...

This paper investigates the potential impact of deep generative models on the work of creative professionals. We argue that current generative modeling tools lack critical features that would make them useful creativity support tools, and introduce our own ...

Natural language processing and other artificial intelligence fields have witnessed impressive progress over the past decade. Although some of this progress is due to algorithmic advances in deep learning, the majority has arguably been enabled by scaling ...

This chapter explores the intersection of generative AI and personalized learning, emphasizing the role of educators and examining the application of large language models (LLMs) in crafting personalized learning paths. The chapter examines the perception ...

Forecasting is a capability inherent in humans when navigating. Humans routinely plan their paths, considering the potential future movements of those around them. Similarly, to achieve comparable sophistication and safety, autonomous systems must embrace ...

Deep learning has emerged as a promising avenue for automatic mapping, demonstrating high efficacy in land cover categorization through various semantic segmentation models. Nonetheless, the practical deployment of these models encounters important challen ...

In this dissertation, we propose multiple methods to improve transfer learning for pretrained language models (PLMs). Broadly, transfer learning is a powerful technique in natural language processing, where a language model is first pre-trained on a data-r ...

Adversarial attacks in Natural Language Processing apply perturbations in the character or token levels. Token-level attacks, gaining prominence for their use of gradient-based methods, are susceptible to altering sentence semantics, leading to invalid adv ...

Prompt–RSVQA: Prompting visual context to a language model for Remote Sensing Visual Question Answering

Chat with Graph Search

Toward universal cell embeddings: integrating single-cell RNA-seq datasets across species with SATURN

Fly-Swat or Cannon? Cost-Effective Language Model Choice via Meta-Modeling

Understanding generalization and robustness in modern deep learning

Incorporating Projective Geometry into Deep Learning

Bayesian Parameter-Efficient Fine-Tuning for Overcoming Catastrophic Forgetting

Efficient local linearity regularization to overcome catastrophic overfitting

Visual Saliency Prediction for Natural Images, Comics Panels, and Comics Pages

Robust machine learning for neuroscientific inference

SVGC-AVA: 360-Degree Video Saliency Prediction With Spherical Vector-Based Graph Convolution and Audio-Visual Attention

Visual complexity of urban streetscapes: human vs computer vision

Serial Dependence in Human Visual Perception and Decision-Making

Predicting Visual Stimuli From Cortical Response Recorded With Wide-Field Imaging in a Mouse

Fast and Future: Towards Efficient Forecasting in Video Semantic Segmentation

Fashioning Creative Expertise with Generative AI: Graphical Interfaces for GAN-Based Design Space Exploration Beter Support Ideation Than Text Prompts for Difusion Models

Text Representation Learning for Low Cost Natural Language Understanding

Can Generative AI Support Educators? Creating Learning Paths with PolyGloT

Deep Generative Models for Autonomous Driving: from Motion Forecasting to Realistic Image Synthesis

Land Cover Mapping From Multiple Complementary Experts Under Heavy Class Imbalance

Improving Generalization of Pretrained Language Models

Revisiting Character-level Adversarial Attacks for Language Models