Related papers: Perceptogram: Reconstructing Visual Percepts and P…

AI-based neural decoding reconstructs visual perception by leveraging generative models to map brain activity, measured through functional MRI (fMRI), into latent hierarchical representations. Traditionally, ridge linear models transform…

We propose an end-to-end learned image compression codec wherein the analysis transform is jointly trained with an object classification task. This study affirms that the compressed latent representation can predict human perceptual…

Electron ptychography describes a family of algorithms which are used to enable the reconstruction of complex specimen transmission functions of a sample in order to obtain both phase and amplitude information, as applied within the realms…

Reconstructing visual stimuli from EEG signals is a crucial step in realizing brain-computer interfaces. In this paper, we propose a transformer-based EEG signal encoder integrating the Discrete Wavelet Transform (DWT) and the gating…

Data-driven flow-field reconstruction typically relies on autoencoder architectures that compress high-dimensional states into low-dimensional latent representations. However, classical approaches such as variational autoencoders (VAEs)…

Understanding how the brain encodes visual information is a central challenge in neuroscience and machine learning. A promising approach is to reconstruct visual stimuli, essentially images, from functional Magnetic Resonance Imaging (fMRI)…

The success of deep learning in computer vision has greatly increased the need for annotated image datasets. We propose an EEG (Electroencephalogram)-based image annotation system. While humans can recognize objects in 20-200 milliseconds,…

The development of EEG decoding algorithms confronts challenges such as data sparsity, subject variability, and the need for precise annotations, all of which are vital for advancing brain-computer interfaces and enhancing the diagnosis of…

Automated interpretation of electrocardiograms (ECG) has garnered significant attention with the advancements in machine learning methodologies. Despite the growing interest, most current studies focus solely on classification or regression…

In this study, we demonstrate the application of a hybrid Vision Transformer (ViT) model, pretrained on ImageNet, on an electroencephalogram (EEG) regression task. Despite being originally trained for image classification tasks, when…

We argue that training autoencoders to reconstruct inputs from noised versions of their encodings, when combined with perceptual losses, yields encodings that are structured according to a perceptual hierarchy. We demonstrate the emergence…

We present a `CLAssifier-DECoder' architecture (\emph{ClaDec}) which facilitates the comprehension of the output of an arbitrary layer in a neural network (NN). It uses a decoder to transform the non-interpretable representation of the…

Human visual reconstruction aims to reconstruct fine-grained visual stimuli based on subject-provided descriptions and corresponding neural signals. As a widely adopted modality, Electroencephalography (EEG) captures rich visual cognition…

Continuous electroencephalography (EEG) is routinely used in neurocritical care to monitor seizures and other harmful brain activity, including rhythmic and periodic patterns that are clinically significant. Although deep learning methods…

Correlative light and electron microscopy is a powerful tool to study the internal structure of cells. It combines the mutual benefit of correlating light (LM) and electron (EM) microscopy information. However, the classical approach of…

In generative modeling, tokenization simplifies complex data into compact, structured representations, creating a more efficient, learnable space. For high-dimensional visual data, it reduces redundancy and emphasizes key features for…

Recent work has shown that learned image compression strategies can outperform standard hand-crafted compression algorithms that have been developed over decades of intensive research on the rate-distortion trade-off. With growing…

Modern Latent Diffusion Models (LDMs) typically operate in low-level Variational Autoencoder (VAE) latent spaces that are primarily optimized for pixel-level reconstruction. To unify vision generation and understanding, a burgeoning trend…

Electroencephalography (EEG) signals reflect activities on certain brain areas. Effective classification of time-varying EEG signals is still challenging. First, EEG signal processing and feature engineering are time-consuming and highly…

Transformers are groundbreaking architectures that have changed a flow of deep learning, and many high-performance models are developing based on transformer architectures. Transformers implemented only with attention with encoder-decoder…