Semantic Segmentation of Benthic Classes in Reef Environments Using a Large Vision Transformer

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.

In recent years, an increasing number of studies have reported on forest declines and shifts in species composition in response to changing climatic conditions (Rigling et al. 2012). The intensification of droughts through rising evaporative demand (i.e., ...

While convolution and self-attention mechanisms have dominated architectural design in deep learning, this survey examines a fundamental yet understudied primitive: the Hadamard product. Despite its widespread implementation across various applications, th ...

As humanity grapples with the escalating challenges of climate change, the discipline of architecture finds itself at a critical juncture. The urgency of the situation demands that schools of architecture not only contribute to envisioning more serene futu ...

The current generation of large language models (LLMs) has limited chemical knowledge. Recently, it has been shown that these LLMs can learn and predict chemical properties through fine-tuning. Using natural language to train machine learning models opens ...

Recent advancements in recommender systems have focused on integrating knowledge graphs (KGs) to leverage their auxiliary information. The core idea of KG-enhanced recommenders is to incorporate rich semantic information for more accurate recommendations. ...

Planning for diverse real-world robotic tasks necessitates to know and write all constraints. However, instances exist where these constraints are either unknown or challenging to specify accurately. A possible solution is to infer the unknown constraints ...

We introduce a new task, novel view synthesis for LiDAR sensors. While traditional model-based LiDAR simulators with style-transfer neural networks can be applied to render novel views, they fall short of producing accurate and realistic LiDAR patterns bec ...

Metal additive manufacturing is a recent breakthrough technology that promises automated production of complex geometric shapes at low operating costs. However, its potential is not yet fully exploited due to the low reproducibility of quality in mass prod ...

Arctic fjords are experiencing rapid environmental shifts due to climate change, which may have significant impacts on marine biodiversity and ecosystem functioning. However, the impact of climate change on fjord biodiversity is difficult to quantify given ...

Unsupervised anomaly detection in medical images such as chest radiographs is stepping into the spotlight as it mitigates the scarcity of the labor-intensive and costly expert annotation of anomaly data. However, nearly all existing methods are formulated ...

Managing divertor plasmas is crucial for operating reactor scale tokamak devices due to heat and particle flux constraints on the divertor target. Simulation is an important tool to understand and control these plasmas, however, for real-time applications ...

The increasing size of deep neural networks (DNNs) necessitates effective model compression to reduce their computational and memory footprints. Sparsity and quantization are two prominent compression methods that have been shown to reduce DNNs' computatio ...

In this thesis, we advocate that Computer-Aided Engineering could benefit from a Geometric Deep Learning revolution, similarly to the way that Deep Learning revolutionized Computer Vision. To do so, we consider a variety of Computer-Aided Engineering pr ...

Shallow ground-source heat pumps (GSHPs) are a promising technology for contributing to the decarbonisation of the energy sector. In heating-dominated climates, the combined use of GSHPs for both heating and cooling increases their technical potential, def ...

Tensors, or multidimensional arrays, are data structures that can naturally represent visual data of multiple dimensions. Inherently able to efficiently capture structured, latent semantic spaces and high-order interactions, tensors have a long history of ...

Transformers achieve remarkable performance in several tasks but due to their quadratic complexity, with respect to the input's length, they are prohibitively slow for very long sequences. To address this limitation, we express the self-attention as a line ...

Semantic Segmentation of Benthic Classes in Reef Environments Using a Large Vision Transformer

Chat with Graph Search

VPDrought – a novel approach to disentangle atmospheric and soil drought in a natural Scots pine forest

Hadamard product in deep learning: Introduction, Advances and Challenges

Transcalar prospects in climate crisis : architectural research in re/action

Assessment of fine-tuned large language models for real-world chemistry and material science applications

Higher-order knowledge-enhanced recommendation with heterogeneous hypergraph multi-attention

Positive-Unlabeled Constraint Learning for Inferring Nonlinear Continuous Constraints Functions From Expert Demonstrations

LiDAR-NeRF: Novel LiDAR View Synthesis via Neural Radiance Fields

Unsupervised quality monitoring of metal additive manufacturing using Bayesian adaptive resonance

Environmental drivers of eukaryotic plankton and fish biodiversity in an Arctic fjord

AMAE: Adaptation of Pre-trained Masked Autoencoder for Dual-Distribution Anomaly Detection in Chest X-Rays

Fast dynamic 1D simulation of divertor plasmas with neural PDE surrogates

Effective Interplay Between Sparsity and Quantization: from Theory to Practice

Synthesis and Analysis of 3D shapes with Geometric Deep Learning in Computer-Aided Engineering

Shallow geothermal energy potential for heating and cooling of buildings with regeneration under climate change scenarios

Tensor Methods in Computer Vision and Deep Learning

Modeling COVID-19 scenarios with a Computable General Equilibrium model

Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention