Related papers: Web image annotation by diffusion maps manifold le…
We have seen significant leapfrog advancement in machine learning in recent decades. The central idea of machine learnability lies on constructing learning algorithms that learn from good data. The availability of more data being made…
Image annotation aims to annotate a given image with a variable number of class labels corresponding to diverse visual concepts. In this paper, we address two main issues in large-scale image annotation: 1) how to learn a rich feature…
Diffusion Map is a spectral dimensionality reduction technique which is able to uncover nonlinear submanifolds in high-dimensional data. And, it is increasingly applied across a wide range of scientific disciplines, such as biology,…
One of the fundamental problems within the field of machine learning is dimensionality reduction. Dimensionality reduction methods make it possible to combat the so-called curse of dimensionality, visualize high-dimensional data and, in…
Detecting road features is a key enabler for autonomous driving and localization. For instance, a reliable detection of poles which are widespread in road environments can improve localization. Modern deep learning-based perception systems…
Non-linear manifold learning enables high-dimensional data analysis, but requires out-of-sample-extension methods to process new data points. In this paper, we propose a manifold learning algorithm based on deep learning to create an…
We propose a weakly-supervised multi-view learning approach to learn category-specific surface mapping without dense annotations. We learn the underlying surface geometry of common categories, such as human faces, cars, and airplanes, given…
Unsupervised learning of feature representations is a challenging yet important problem for analyzing a large collection of multimedia data that do not have semantic labels. Recently proposed neural network-based unsupervised learning…
Recent research in the field of computer vision strongly focuses on deep learning architectures to tackle image processing problems. Deep neural networks are often considered in complex image processing scenarios since traditional computer…
Image search and retrieval engines rely heavily on textual annotation in order to match word queries to a set of candidate images. A system that can automatically annotate images with meaningful text can be highly beneficial for such…
High-quality labeled datasets are essential for deep learning. Traditional manual annotation methods are not only costly and inefficient but also pose challenges in specialized domains where expert knowledge is needed. Self-supervised…
Deep neural networks (DNNs) have demonstrated exceptional performance across various image segmentation tasks. However, the process of preparing datasets for training segmentation DNNs is both labor-intensive and costly, as it typically…
Few-shot learning algorithms aim to learn model parameters capable of adapting to unseen classes with the help of only a few labeled examples. A recent regularization technique - Manifold Mixup focuses on learning a general-purpose…
In recent years, computer vision has transformed fields such as medical imaging, object recognition, and geospatial analytics. One of the fundamental tasks in computer vision is semantic image segmentation, which is vital for precise object…
Build accurate DNN models requires training on large labeled, context specific datasets, especially those matching the target scenario. We believe advances in wireless localization, working in unison with cameras, can produce automated…
Recent advances in data-centric artificial intelligence highlight inherent limitations in object recognition datasets. One of the primary issues stems from the semantic gap problem, which results in complex many-to-many mappings between…
Cross-modal retrieval between visual data and natural language description remains a long-standing challenge in multimedia. While recent image-text retrieval methods offer great promise by learning deep representations aligned across…
Inverting visual representations within deep neural networks (DNNs) presents a challenging and important problem in the field of security and privacy for deep learning. The main goal is to invert the features of an unidentified target image…
High-level 3D scene understanding is essential in many applications. However, the challenges of generating accurate 3D annotations make development of deep learning models difficult. We turn to recent advancements in automatic retrieval of…
We study the theoretical behavior of denoising score matching--the learning task associated to diffusion models--when the data distribution is supported on a low-dimensional manifold and the score is parameterized using a random feature…