Newest papers

Multiclass Boundary Refinement with Neural Cellular Automata for Remote Sensing Land Cover Segmentation

Pascoassis Souza Santos Meira, Gilson Antonio Giraldi, Rafael Duarte Coelho dos Santos · 2026 · arXiv

DOI: 10.48550/arXiv.2610.30007 · open-access PDF

Spanish

La segmentación semántica de las imágenes de detección remota a menudo coloca los límites de la clase a unos pocos píxeles de donde realmente se encuentran, y este error de posición se concentra en la banda delgada medida por la IoU de frontera (BIoU). Tratamos el refinamiento de la frontera como la aplicación iterada de una pequeña regla local aprendida: el Automatón Neural de Refinamiento de la Célula de la Frontera (BRNCA), que comienza con las probabilidades de clase de un segmentador congelado, pre-entrenado y las corrige célula por célula. Generalizamos el rNCA binario al caso multiclásico manteniendo los canales visibles en el simplex de probabilidad a través de un Aitchison.

Machine translation (Meta M2M100); the English original follows.

Abstract

Semantic segmentation of remote sensing imagery often places class boundaries a few pixels away from where they truly lie, and this position error is concentrated in the thin band measured by Boundary IoU (BIoU). We treat boundary refinement as the iterated application of a small learned local rule: the Boundary Refinement Neural Cellular Automaton (BRNCA), that starts from the class probabilities of a frozen, pre-trained segmenter and corrects them cell by cell. We generalise the binary rNCA to the multiclass case by keeping the visible channels on the probability simplex through an Aitchison

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.30007, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange