arXiv subjects

Roberto M. Cesar Jr.

Publications and source records attributed to Roberto M. Cesar Jr..

7 recordsLinked to original sources

arXiv2026

Graph Memory: A Structured and Interpretable Framework for Modality-Agnostic Embedding-Based Inference

We introduce Graph Memory (GM), a structured non-parametric framework that represents an embedding space through a compact graph of reliability-annotated prototype regions. GM encodes local geometry and regional ambiguity through prototype relations and performs inference by diffusing query evidence across this structure, unifying instance retrieval, prototype-based reasoning, and graph diffusion within a single inductive and interpretable model. The framework is inherently modality-agnostic: in multimodal settings, independent prototype graphs are constructed for each modality and their calibrated predictions are combined through reliability-aware late fusion, enabling transparent integration of heterogeneous sources such as whole-slide images and gene-expression profiles. Experiments on synthetic benchmarks, breast histopathology (IDC), and the multimodal AURORA dataset show that GM matches or exceeds the accuracy of kNN and Label Spreading while providing substantially better calibration, smoother decision boundaries, and an order-of-magnitude smaller memory footprint. By explicitly modeling regional reliability and relational structure, GM offers a principled and interpretable approach to non-parametric inference across single- and multi-modal domains.

cs.LG↗

arXiv2025

DPFlow: Adaptive Optical Flow Estimation with a Dual-Pyramid Framework

Optical flow estimation is essential for video processing tasks, such as restoration and action recognition. The quality of videos is constantly increasing, with current standards reaching 8K resolution. However, optical flow methods are usually designed for low resolution and do not generalize to large inputs due to their rigid architectures. They adopt downscaling or input tiling to reduce the input size, causing a loss of details and global information. There is also a lack of optical flow benchmarks to judge the actual performance of existing methods on high-resolution samples. Previous works only conducted qualitative high-resolution evaluations on hand-picked samples. This paper fills this gap in optical flow estimation in two ways. We propose DPFlow, an adaptive optical flow architecture capable of generalizing up to 8K resolution inputs while trained with only low-resolution samples. We also introduce Kubric-NK, a new benchmark for evaluating optical flow methods with input resolutions ranging from 1K to 8K. Our high-resolution evaluation pushes the boundaries of existing methods and reveals new insights about their generalization capabilities. Extensive experimental results show that DPFlow achieves state-of-the-art results on the MPI-Sintel, KITTI 2015, Spring, and other high-resolution benchmarks.

cs.CV↗

arXiv2025

Creating User-steerable Projections with Interactive Semantic Mapping

Dimensionality reduction (DR) techniques map high-dimensional data into lower-dimensional spaces. Yet, current DR techniques are not designed to explore semantic structure that is not directly available in the form of variables or class labels. We introduce a novel user-guided projection framework for image and text data that enables customizable, interpretable, data visualizations via zero-shot classification with Multimodal Large Language Models (MLLMs). We enable users to steer projections dynamically via natural-language guiding prompts, to specify high-level semantic relationships of interest to the users which are not explicitly present in the data dimensions. We evaluate our method across several datasets and show that it not only enhances cluster separation, but also transforms DR into an interactive, user-driven process. Our approach bridges the gap between fully automated DR techniques and human-centered data exploration, offering a flexible and adaptive way to tailor projections to specific analytical needs.

cs.LG↗

arXiv2025

A Systematic Approach for Studying How Topological Measurements Respond to Complex Networks Modifications

Different types of graphs and complex networks have been characterized, analyzed, and modeled based on measurements of their respective topology. However, the available networks may constitute approximations of the original structure as a consequence of sampling incompleteness, noise, and/or error in the representation of that structure. Therefore, it becomes of particular interest to quantify how successive modifications may impact a set of adopted topological measurements, and how respectively undergone changes can be interrelated, which has been addressed in this paper by considering similarity networks and hierarchical clustering approaches. These studies are developed respectively to several topological measurements (accessibility, degree, hierarchical degree, clustering coefficient, betweenness centrality, assortativity, and average shortest path) calculated from complex networks of three main types (Erdős-Rényi, Barabási-Albert, and geographical) with varying sizes or subjected to progressive edge removal or rewiring. The coincidence similarity index, which can implement particularly strict comparisons, is adopted for two main purposes: to quantify and visualize how the considered topological measurements respond to the considered network alterations and to represent hierarchically the relationships between the observed changes undergone by the considered topological measurements. Several results are reported and discussed, including the identification of three types of topological changes taking place as a consequence of the modifications. In addition, the changes observed for the Erdős-Rényi and Barabási-Albert networks resulted mutually more similarly affected by topological changes than for the geometrical networks. The latter type of network has been identified to have more heterogeneous topological features than the other two types of networks.

cs.SI↗

arXiv2024

Node Accessibility Characterization of Radially-Grown Structures

Complex systems have motivated continuing interest from the scientific community, leading to new concepts and methods. Growing systems represent a case of particular interest, as their topological, geometrical, and also dynamical properties change along time, as new elements are incorporated into the existing structure. In the present work, an approach is the case in which systems grown radially around some straight axis of reference, such as particle deposition on electrodes, or urban expansion along avenues, roads, coastline, or rivers, among several other possibilities. More specifically, we aim at characterizing the topological properties of simulated growing structures, which are represented as graphs, in terms of a measurement corresponding to the accessibility of each involved node. The incorporation of new elements (nodes and links) is performed preferentially to the angular orientation respectively to the reference axis. Several interesting results are reported, including the tendency of structures grown preferentially to the orientation normal to the axis to have smaller accessibility.

cs.SI↗

arXiv2021

Template-Based Graph Clustering

We propose a novel graph clustering method guided by additional information on the underlying structure of the clusters (or communities). The problem is formulated as the matching of a graph to a template with smaller dimension, hence matching $n$ vertices of the observed graph (to be clustered) to the $k$ vertices of a template graph, using its edges as support information, and relaxed on the set of orthonormal matrices in order to find a $k$ dimensional embedding. With relevant priors that encode the density of the clusters and their relationships, our method outperforms classical methods, especially for challenging cases.

stat.ML↗

arXiv2006

Retinal Vessel Segmentation Using the 2-D Morlet Wavelet and Supervised Classification

We present a method for automated segmentation of the vasculature in retinal images. The method produces segmentations by classifying each image pixel as vessel or non-vessel, based on the pixel's feature vector. Feature vectors are composed of the pixel's intensity and continuous two-dimensional Morlet wavelet transform responses taken at multiple scales. The Morlet wavelet is capable of tuning to specific frequencies, thus allowing noise filtering and vessel enhancement in a single step. We use a Bayesian classifier with class-conditional probability density functions (likelihoods) described as Gaussian mixtures, yielding a fast classification, while being able to model complex decision surfaces and compare its performance with the linear minimum squared error classifier. The probability distributions are estimated based on a training set of labeled pixels obtained from manual segmentations. The method's performance is evaluated on publicly available DRIVE and STARE databases of manually labeled non-mydriatic images. On the DRIVE database, it achieves an area under the receiver operating characteristic (ROC) curve of 0.9598, being slightly superior than that presented by the method of Staal et al.

cs.CV↗