Related papers: FATE: Feature-Agnostic Transformer-based Encoder f…

Specialised transformers-based models (such as BioBERT and BioMegatron) are adapted for the biomedical domain based on publicly available biomedical corpora. As such, they have the potential to encode large-scale biological knowledge. We…

Self-supervised learning has revolutionized medical imaging by enabling efficient and generalizable feature extraction from large-scale unlabeled datasets. Recently, self-supervised foundation models have been extended to three-dimensional…

Weakly-supervised anomaly detection aims at learning an anomaly detector from a limited amount of labeled data and abundant unlabeled data. Recent works build deep neural networks for anomaly detection by discriminatively mapping the normal…

In contrast with previous approaches where information flows only towards deeper layers of a stack, we consider a multi-pass transformer (MPT) architecture in which earlier layers are allowed to process information in light of the output of…

With the wide and deep adoption of deep learning models in real applications, there is an increasing need to model and learn the representations of the neural networks themselves. These models can be used to estimate attributes of different…

Resonant anomaly detection is a promising framework for model-independent searches for new particles. Weakly supervised resonant anomaly detection methods compare data with a potential signal against a template of the Standard Model (SM)…

Hippocampal formation (HF) can rapidly adapt to varied environments and build flexible working memory (WM). To mirror the HF's mechanism on generalization and WM, we propose a model named Generalization and Associative Temporary Encoding…

We study the intrinsic transformation of feature maps across convolutional network layers with explicit top-down control. To this end, we develop top-down feature transformer (TFT), under controllable parameters, that are able to account…

In this work, we propose a flow-adapter architecture for unsupervised NMT. It leverages normalizing flows to explicitly model the distributions of sentence-level latent representations, which are subsequently used in conjunction with the…

Adopting Convolutional Neural Networks (CNNs) in the daily routine of primary diagnosis requires not only near-perfect precision, but also a sufficient degree of generalization to data acquisition shifts and transparency. Existing CNN…

Cross-domain few-shot learning (CD-FSL) requires models to generalize from limited labeled samples under significant distribution shifts. While recent methods enhance adaptability through lightweight task-specific modules, they operate…

Latent space models for network data characterize each node through a vector of latent features whose pairwise similarities define the edge probabilities among the pairs of nodes. Although this formulation has led to successful…

Transformers have become methods of choice in many applications thanks to their ability to represent complex interactions between elements. However, extending the Transformer architecture to non-sequential data such as molecules and…

Network traffic analysis is fundamental for network management, troubleshooting, and security. Tasks such as traffic classification, anomaly detection, and novelty discovery are fundamental for extracting operational information from…

The recent popularity of foundation models and the pre-train-and-adapt paradigm, where a large-scale model is transferred to downstream tasks, is gaining attention for volumetric medical image segmentation. However, current transfer…

One of the main challenges of Topological Data Analysis (TDA) is to extract features from persistent diagrams directly usable by machine learning algorithms. Indeed, persistence diagrams are intrinsically (multi-)sets of points in…

Exemplar-based image translation refers to the task of generating images with the desired style, while conditioning on certain input image. Most of the current methods learn the correspondence between two input domains and lack the mining…

Unsupervised domain adaptation (UDA) aims to leverage the knowledge learned from labeled source domains to improve performance on the unlabeled target domains. While Convolutional Neural Networks (CNNs) have been dominant in previous UDA…

Learned image compression (LIC) has gained traction as an effective solution for image storage and transmission in recent years. However, existing LIC methods are redundant in latent representation due to limitations in capturing…

Generative models that learn disentangled representations for different factors of variation in an image can be very useful for targeted data augmentation. By sampling from the disentangled latent subspace of interest, we can efficiently…