Related papers: Generative Restricted Kernel Machines: A Framework…

The paper introduces the Hidden Tree Markov Network (HTN), a neuro-probabilistic hybrid fusing the representation power of generative models for trees with the incremental and discriminative learning capabilities of neural networks. We put…

The scaling of large language models to encode all the world's knowledge in model parameters is unsustainable and has exacerbated resource barriers. Retrieval-Augmented Generation (RAG) presents a potential solution, yet its application to…

Suffering from the semantic insufficiency and domain-shift problems, most of existing state-of-the-art methods fail to achieve satisfactory results for Zero-Shot Learning (ZSL). In order to alleviate these problems, we propose a novel…

In this paper, we propose a novel supervised learning method that is called Deep Embedding Kernel (DEK). DEK combines the advantages of deep learning and kernel methods in a unified framework. More specifically, DEK is a learnable kernel…

In image-based camera localization systems, information about the environment is usually stored in some representation, which can be referred to as a map. Conventionally, most maps are built upon hand-crafted features. Recently, neural…

We present a probabilistic viewpoint to multiple kernel learning unifying well-known regularised risk approaches and recent advances in approximate Bayesian inference relaxations. The framework proposes a general objective function suitable…

This paper presents a brief introduction to the key points of the Grey Machine Learning (GML) based on the kernels. The general formulation of the grey system models have been firstly summarized, and then the nonlinear extension of the grey…

Utilization of classification latent space information for downstream reconstruction and generation is an intriguing and a relatively unexplored area. In general, discriminative representations are rich in class-specific features but are…

Kernel-based methods exhibit well-documented performance in various nonlinear learning tasks. Most of them rely on a preselected kernel, whose prudent choice presumes task-specific prior information. Especially when the latter is not…

Training effective Generative Adversarial Networks (GANs) requires large amounts of training data, without which the trained models are usually sub-optimal with discriminator over-fitting. Several prior studies address this issue by…

Multimodal learning is a framework for building models that make predictions based on different types of modalities. Important challenges in multimodal learning are the inference of shared representations from arbitrary modalities and…

Graph Foundation Models (GFMs) have emerged as a frontier in graph learning, which are expected to deliver transferable representations across diverse tasks. However, GFMs remain constrained by in-memory bottlenecks: they attempt to encode…

Representation learning is an important step in the machine learning pipeline. Given the current biological sequencing data volume, learning an explicit representation is prohibitive due to the dimensionality of the resulting feature…

In this work, we focus on synthesizing high-fidelity novel view images for arbitrary human performers, given a set of sparse multi-view images. It is a challenging task due to the large variation among articulated body poses and heavy…

Generative models have achieved state-of-the-art performance for the zero-shot learning problem, but they require re-training the classifier every time a new object category is encountered. The traditional semantic embedding approaches,…

Recent image degradation estimation methods have enabled single-image super-resolution (SR) approaches to better upsample real-world images. Among these methods, explicit kernel estimation approaches have demonstrated unprecedented…

Generative models have made it possible to synthesize highly realistic images, potentially providing an abundant data source for training machine learning models. Despite the advantages of these synthesizable data sources, the…

The availability of large-scale annotated image datasets and recent advances in supervised deep learning methods enable the end-to-end derivation of representative image features that can impact a variety of image analysis problems. Such…

Recent self-supervised contrastive learning provides an effective approach for unsupervised person re-identification (ReID) by learning invariance from different views (transformed versions) of an input. In this paper, we incorporate a…

We propose a framework of generative adversarial networks with multiple discriminators, which collaborate to represent a real dataset more effectively. Our approach facilitates learning a generator consistent with the underlying data…