CORTEXA
← Browse
arxivcs.CVcs.AIcs.LG2026-07-15

Multi-Expert Routing for Multi-Domain Low-Resource OCR: A Manchu Case Study

Zhan Chen, Jiqiao Ma, Chih-wen Kuo

Historical Manchu OCR must accommodate various visually distinct writing styles, including regular script, running script, and the semi-cursive chancery hand used in palace memorials, despite limited labeled data. We study a multi-expert system that reuses checkpoints from an iterative fine-tuning process as domain specialists and uses a lightweight page-level image classifier to dispatch pages by visual style. When the checkpoint pool lacks a suitable specialist, we train an additional expert for that domain. On three frozen test sets, the routed system matches the selected specialist for each style at two-decimal precision: 0.30 percent CER on regular script, 1.57 percent on memorials, and 4.83 percent on running script. The router achieves 99.3 percent page-level domain accuracy and matches the domain-label oracle at the same precision. Two of the three selected specialists were not trained specifically for their final domain; only the running-script expert was trained with that domain as its target. We report the evaluation protocol, router design, and per-page predictions to make the comparison reproducible.

View free PDFSource page

Related papers

arxivcs.LGcs.AIcs.CV2026-06-30

FedCC: A Low-Resource Federated Adaptation of Foundation Models for Robust Corpus Callosum localization in Fetal Ultrasound Images

Alessandro Di Matteo, Sara Moccia, Giuseppe Rizzo, Gianpaolo Grisolia, Ricciarda Raffaelli, Lorenzo Vasciaveo, et al.

Accurate localization of the corpus callosum (CC) in fetal ultrasound (US) images is crucial for the early identification of neurodevelopmental abnormalities. However, this task remains highly challenging due to the intrinsic limitations of US imaging, including low contrast, spe…

View free PDFSource page
arxivcs.LGcs.AIcs.CV2026-07-02

Do Newer Lightweight CNNs Perform Better Under Resource Constraints? A Controlled Multigenerational Study of Architecture, Initialization, Training Budget, and Efficiency

Tasnim Shahriar

Newer lightweight convolutional neural networks are often presented as improving predictive performance and deployment efficiency, but such claims require controlled evaluation. This study compares nine lightweight CNN model packages across CIFAR-10, CIFAR-100, and Tiny ImageNet…

View free PDFSource page
arxivcs.LGcs.AIcs.CV2026-07-20

Now We Know? A Systematic Comparison of TerraMind and THOR

Frederick Schindlegger, Kenzo Bounegta, Eva Gmelich Meijling, Johannes Jakubik, Arnt-Børre Salberg, Theodor Forgaard, et al.

Benchmarks for Geospatial Foundation Models (GFMs) increasingly rank models by aggregate score, but such rankings obscure why models differ: how much of the gap is architecture, how much is decoder capacity, and how much is a use-case-specific artefact? This study addresses that…

View free PDFSource page
arxivcs.LGcs.AIcs.CV2026-07-01

Multi-modal Rail Crossing Safety Analysis

Paimon Goulart, Chansong Lim, Nícolas Roque dos Santos, Yue Dong, Sheldon Peterson, Jia Chen, et al.

Given one or more images of a railway crossing, can we leverage visual cues that allow us to robustly estimate how safe it is? Can we improve our ability to do so by introducing structured data (such as official accident reports) about the accident history of that crossing into o…

View free PDFSource page
arxivcs.CLcs.AIcs.CVcs.LG2026-06-25

Empowering GUI Agents via Autonomous Experience Exploration and Hindsight Experience Utilization for Task Planning

Tianyi Men, Zhuoran Jin, Pengfei Cao, Yubo Chen, Kang Liu, Jun Zhao

Multimodal web agents can assist humans in operating repetitive GUI tasks, where effective task planning is essential for decomposing complex tasks into executable actions. While small open source MLLMs are cost efficient and privacy preserving compared with commercial large mode…

View free PDFSource page
arxivcs.CVcs.AIcs.LG2026-06-29

Few-Shot Domain Incremental Learning via Continual Vision-Language Consolidation

Naeem Paeedeh, Mahardhika Pratama, Wolfgang Mayer, Mukesh Prasad, Weiping Ding, Yew-Soon Ong

Existing domain-incremental learning (DIL) strategies call for massive amounts of data to adapt to new domains and suffer from the overfitting problem in the case of data scarcity. This paper puts forward a relatively uncharted problem, namely, few-shot domain incremental learnin…

View free PDFSource page