Related papers: vONTSS: vMF based semi-supervised neural topic mod…

Variational inference is a very efficient and popular heuristic used in various forms in the context of latent variable models. It's closely related to Expectation Maximization (EM), and is applied when exact EM is computationally…

Self-supervised learning (SSL) has emerged as a promising technique for analyzing medical modalities such as X-rays due to its ability to learn without annotations. However, conventional SSL methods face challenges in achieving semantic…

Traditional neural topic models are typically optimized by reconstructing the document's Bag-of-Words (BoW) representations, overlooking contextual information and struggling with data sparsity. In this work, we propose a novel approach to…

Several supermodular losses have been shown to improve the perceptual quality of image segmentation in a discriminative framework such as a structured output support vector machine (SVM). These loss functions do not necessarily have the…

We propose a novel generative model to explore both local and global context for joint learning topics and topic-specific word embeddings. In particular, we assume that global latent topics are shared across documents, a word is generated…

Supervisory signals have the potential to make low-dimensional data representations, like those learned by mixture and topic models, more interpretable and useful. We propose a framework for training latent variable models that explicitly…

Brain network analysis provides an interpretable framework for characterizing brain organization and has been widely used for neurological disorder identification. Recent advances in self-supervised learning have motivated the development…

Vision Transformer (ViT) models have recently emerged as powerful and versatile models for various visual tasks. Recently, a work called PMF has achieved promising results in few-shot image classification by utilizing pre-trained vision…

Topic models are one of the most popular methods for learning representations of text, but a major challenge is that any change to the topic model requires mathematically deriving a new inference algorithm. A promising approach to address…

Multitarget Tracking (MTT) is the problem of tracking the states of an unknown number of objects using noisy measurements, with important applications to autonomous driving, surveillance, robotics, and others. In the model-based Bayesian…

Single-molecule localization microscopy (SMLM) allows reconstructing biology-relevant structures beyond the diffraction limit by detecting and localizing individual fluorophores -- fluorescent molecules stained onto the observed specimen --…

Automated brain tumor segmentation based on deep learning (DL) has achieved promising performance. However, it generally relies on annotated images for model training, which is not always feasible in clinical settings. Therefore, the…

Topic models aim to reveal latent structures within a corpus of text, typically through the use of term-frequency statistics over bag-of-words representations from documents. In recent years, conceptual entities -- interpretable,…

This paper presents a study on semi-supervised learning to solve the visual attribute prediction problem. In many applications of vision algorithms, the precise recognition of visual attributes of objects is important but still challenging.…

This paper proposes a novel semi-supervised TTS framework, QS-TTS, to improve TTS quality with lower supervised data requirements via Vector-Quantized Self-Supervised Speech Representation Learning (VQ-S3RL) utilizing more unlabeled speech…

Neural machine translation, a recently proposed approach to machine translation based purely on neural networks, has shown promising results compared to the existing approaches such as phrase-based statistical machine translation. Despite…

Long-tailed learning aims to tackle the crucial challenge that head classes dominate the training procedure under severe class imbalance in real-world scenarios. However, little attention has been given to how to quantify the dominance…

This thesis presents new methods for unsupervised learning of distributed representations of words and entities from text and knowledge bases. The first algorithm presented in the thesis is a multi-view algorithm for learning…

Functional alignment between subjects is an important assumption of functional magnetic resonance imaging (fMRI) group-level analysis. However, it is often violated in practice, even after alignment to a standard anatomical template.…

Semi-supervised learning for medical image segmentation is an important area of research for alleviating the huge cost associated with the construction of reliable large-scale annotations in the medical domain. Recent semi-supervised…