{
  "abstract": "Data leakage, the unintentional use of illegitimate information during model training, fundamentally undermines the validity of machine learning evaluations. While well-documented in theory, a critical and pervasive manifestation, improper sequencing of data augmentation relative to dataset splitting remains a frequently overlooked issue in practice. This pre-split application of augmentation violates the core independence assumption between training and test data, allowing models to memorize augmentation artifacts rather than learn generalizable features. Through rigorous reproducibility case studies in agricultural computer vision, we quantify the severe inflationary effect of this methodological flaw. Re-evaluating the work of Joshi et al. with a correct split-then-augment protocol reveals a performance drop from 98.70% to 32.77% mAP50, a reduction of 65.93 percentage points. A second case study on rice pest detection (Yin et al.) confirms this pattern, with a performance decrease from 99.5% to 89.1% after correcting for data leakage and near-duplicates.This analysis identifies two distinct leakage pathways, categorized as process-induced (improper augmentation sequence) and data-inherent (undetected duplicates in benchmarks). Contextualizing our findings within broader literature, we show how this error is perpetuated by educational gaps, tool design, and academic incentives. To mitigate these risks, a comprehensive set of actionable best practices for researchers, reviewers and educators is proposed. These include rigorous data integrity protocols, enhanced methodological checklists in peer reviews and a paradigm shift towards pitfalls-based learning. Our work underscores that preventing data leakage is not merely a technicality but a prerequisite for reliable and reproducible machine learning, with implications for computer vision and beyond.",
  "abstract_shown": true,
  "affiliations": [
    "Cologne Lab for Artificial Intelligence and Smart Automation (CAISA), Institute of Product Development and Engineering Design (IPK), TH Köln – University of Applied Sciences, Cologne, Germany, Betzdorfer Straße 2, 50679, Cologne, Germany"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 2,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Fabian Gerz",
      "orcid": "0009-0006-0163-2132"
    },
    {
      "affs": [
        0
      ],
      "name": "Mohieddine Jelali",
      "orcid": "0000-0002-0347-9913"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/4nxy2amst737g.bib",
  "cited_by": 8,
  "doi": "10.1016/j.atech.2026.102462",
  "fulltext_url": null,
  "id": "4nxy2amst737g",
  "issns": [
    "2772-3755"
  ],
  "landing_url": "https://doi.org/10.1016/j.atech.2026.102462",
  "language": "en",
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "1110|Smart Agriculture and AI"
    ]
  ],
  "openalex": "W7202038640",
  "pdf_url": null,
  "pmcid": null,
  "pmid": null,
  "published": "2026-08-10",
  "publisher": "Elsevier BV",
  "ris": "https://research.draconitic.com/paper/4nxy2amst737g.ris",
  "sources": [
    {
      "first_seen": "2026-11-04T13:21:08Z",
      "native_id": "W7202038640",
      "source": "openalex",
      "url": "https://doi.org/10.1016/j.atech.2026.102462"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "openalex:1110|Smart Agriculture and AI",
      "subfield": "plant-biology"
    }
  ],
  "title": "Towards reliable data augmentation in machine learning: Practices to prevent data leakage",
  "title_text": "Towards reliable data augmentation in machine learning: Practices to prevent data leakage",
  "type": "peer-reviewed",
  "updated_at": "2026-11-09T13:21:08Z",
  "url": "https://research.draconitic.com/paper/4nxy2amst737g",
  "venue": "Smart Agricultural Technology",
  "versions": []
}