Rethinking Pretraining for Specialized Design Data: Evidence from the JONES-19 Cultural Design Dataset

• URL: http://arxiv.org/abs/2608.00135v1
• Date: Fri, 31 Jul 2026 14:12:09 GMT
• Title: Rethinking Pretraining for Specialized Design Data: Evidence from the JONES-19 Cultural Design Dataset
• Abstract summary: Design and architectural archives encode expert human knowledge in graphical formats.<n>We evaluate the discriminative performance of Convolutional Neural Networks (CNNs) in two model training strategies.
• Score: 45.88028371034407
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Design and architectural archives encode expert human knowledge in graphical formats, providing a critical testbed for design-inspired Machine Learning (ML) challenges absent with typical computer vision benchmarks. Building on JONES-19, a small-size image dataset based on The Grammar of Ornament (London, 1857), we evaluate the discriminative performance of Convolutional Neural Networks (CNNs) in two model training strategies: (a) ImageNet pretraining for domain-general "visual common sense," and (b) learning from scratch on the design data in JONES-19. We find that while domain-general priors improve discriminative performance, learning from scratch augmented with repeated local sampling (multi-crop) effectively recovers these gains. For highly structured design data, local design-driven representations provide sufficient foundation for learning, challenging a reliance on massive general-purpose pretraining. These findings suggest that in specialized design domains, careful curation of smaller high-quality datasets that capture empirical and formal design principles may prove more effective and informative on the nature of a particular design domain than prioritizing large-scale data collection.

Related papers

• Visual graphs for image classification: does the structure affect performance? [51.56484100374058]
  This work aims to conduct a systematic comparison of current graph construction techniques within the context of a fixed three-layer GCN architecture.<n>It demonstrates in particular how the network structure affects performance and provides an important methodological contribution regarding the computational stages preceding graph utilization.
  arXiv  Detail & Related papers  (2026-07-07T14:01:44Z)
• Training a Custom CNN on Five Heterogeneous Image Datasets [1.4583375893645076]
  This study investigates the effectiveness of CNN-based architectures across five datasets spanning agricultural and urban domains.<n>These datasets introduce varying challenges, including differences in illumination, resolution, environmental complexity, and class imbalance.<n>We evaluate a lightweight, task-specific custom CNN alongside established deep architectures, including ResNet-18 and VGG-16, trained both from scratch and using transfer learning.
  arXiv  Detail & Related papers  (2026-01-08T08:44:17Z)
• Evolving CNN Architectures: From Custom Designs to Deep Residual Models for Diverse Image Classification and Detection Tasks [0.9023847175654603]
  This paper presents a comparative study of a custom convolutional neural network (CNN) architecture against widely used pretrained and transfer learning CNN models.<n>The datasets span binary classification, fine-grained multiclass recognition, and object detection scenarios.<n>We analyze how architectural factors, such as network depth, residual connections, and feature extraction strategies, influence classification and localization performance.
  arXiv  Detail & Related papers  (2026-01-03T07:45:08Z)
• A Guide to Robust Generalization: The Impact of Architecture, Pre-training, and Optimization Strategy [50.33847176405776]
  We present an empirical study spanning 6 datasets, 40 pretrained architectures, 2 specialized losses, and 3 adaptation protocols.<n>We find that convolutional neural networks pretrained in a supervised manner on large datasets often perform best.
  arXiv  Detail & Related papers  (2025-08-12T19:38:35Z)
• Copresheaf Topological Neural Networks: A Generalized Deep Learning Framework [16.903981913294103]
  We introduce copresheaf topological neural networks (CTNNs)<n>CTNNs are a powerful unifying framework that encapsulates a wide spectrum of deep learning architectures.<n>We show that CTNNs consistently outperform conventional baselines in tasks requiring hierarchical or localized sensitivity.
  arXiv  Detail & Related papers  (2025-05-27T14:28:50Z)
• Implicitly Guided Design with PropEn: Match your Data to Follow the Gradient [52.2669490431145]
  PropEn is inspired by'matching', which enables implicit guidance without training a discriminator. We show that training with a matched dataset approximates the gradient of the property of interest while remaining within the data distribution.
  arXiv  Detail & Related papers  (2024-05-28T11:30:19Z)
• Privacy-preserving design of graph neural networks with applications to vertical federated learning [56.74455367682945]
  We present an end-to-end graph representation learning framework called VESPER. VESPER is capable of training high-performance GNN models over both sparse and dense graphs under reasonable privacy budgets.
  arXiv  Detail & Related papers  (2023-10-31T15:34:59Z)
• Digital Fingerprinting of Microstructures [44.139970905896504]
  Finding efficient means of fingerprinting microstructural information is a critical step towards harnessing data-centric machine learning approaches. Here, we consider microstructure classification and utilise the resulting features over a range of related machine learning tasks. In particular, methods that leverage transfer learning with convolutional neural networks (CNNs), pretrained on the ImageNet dataset, are generally shown to outperform other methods.
  arXiv  Detail & Related papers  (2022-03-25T15:40:44Z)
• On the Suitability of Neural Networks as Building Blocks for The Design of Efficient Learned Indexes [0.0]
  An emerging trend is to combine Machine Learning techniques with the ones proper of Data Structures. This new area goes under the name of Learned Data Structures. We provide the first, and much needed, comparative experimental analysis regarding the use of Neural Networks as building blocks of Learned Data Structures.
  arXiv  Detail & Related papers  (2022-02-21T11:15:40Z)
• A Design Space Study for LISTA and Beyond [79.76740811464597]
  In recent years, great success has been witnessed in building problem-specific deep networks from unrolling iterative algorithms. This paper revisits the role of unrolling as a design approach for deep networks, to what extent its resulting special architecture is superior, and can we find better? Using LISTA for sparse recovery as a representative example, we conduct the first thorough design space study for the unrolled models.
  arXiv  Detail & Related papers  (2021-04-08T23:01:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.