Writing study: Data Leakage Detection and De-duplication in Large Scale Geospatial Image Datasets

CVPR overviewCorpus atlasBy contribution typeVisual galleryRules & templateWriting patternsPaper studies

← CVPR 2026 oral writing corpus

Yeshwanth Kumar Adimoolam, Charalambos Poullis, Melinos Averkiou · Official CVPR 2026 oral record

Observed writing choices, not acceptance rules. This study examines the inspected manuscript version. It does not establish why the paper was accepted or that its presentation choices should be copied unchanged.

Figure, table and section ledger

Editorial contribution type: Empirical analysis, diagnosis & auditing (primary).

Layout extraction, not a required paper template. Counts are distinct caption labels; a multi-panel figure counts once. Section spans are estimated from heading positions, including floats and whitespace. Method and limitations.

Canonical PDF

10 physical pages

Before references / appendix

≈ 8.13 page-equivalents

Main figures / tables

4 / 4

Attached appendix figures / tables

0 / 0

Attached appendix span

Separate file recorded below; not in this PDF total

Before references / appendix: ≈ 81.3%References / intervening material: ≈ 18.7%Estimated layout envelopes, not text/artwork area. Unresolved appendix boundaries remain within the undivided post-body material.

Extraction notes: No attached appendix boundary detected. Zero means no recognized caption, not independently verified absence.

Section-by-section lengths and source pages

The title/abstract/front matter precede the first numbered heading. A span ends at the next detected top-level heading, not at the last sentence; end-page whitespace is included. References and statements are listed separately. These are not measurements of text-only or artwork area.

Top-level heading	Starts on PDF page	Estimated span	Share of entire PDF
1. Introduction	1	≈ 0.96 pp.	9.6%
2. Related Works	2	≈ 0.81 pp.	8.1%
3. Methodology	3	≈ 0.64 pp.	6.4%
4. Experiments and Results	3	≈ 3.64 pp.	36.4%
5. Conclusion and Discussion	7	≈ 1.64 pp.	16.4%
Acknowledgements	9	≈ 0.08 pp.	0.8%
References	9	≈ 1.87 pp.	18.7%

All detected figure and table locations

Main text

• Figure 1 · p. 4
• Table 1 · p. 5
• Table 2 · p. 5
• Table 3 · p. 5
• Figure 2 · p. 6
• Figure 3 · p. 7
• Table 4 · p. 7
• Figure 4 · p. 8

Attached appendix

No recognized caption labels.

Separate source files—excluded from canonical-PDF totals

A separate author version may repeat main text and references. Whole-file lengths and counts are not extra appendix material and are never added to the canonical PDF totals. Read the study's source scope for which sections received substantive reading versus layout inspection.

Additional source 1

Separate PDF (or ZIP containing it): whole-file layout of 5 physical pages; 5 detected figures and 2 tables. These may include overlapping main-text material.

Located appendix only: starts on physical p.1; ≈ 4.85 page-equivalents, 5 figure labels and 2 table labels. This interval is distinct from the whole file.

Detected heading	PDF page	Estimated span
Supplementary Material	1	≈ 0.04 pp.
6. Data Leakage and Overfitting	1	≈ 0.36 pp.
7. PHash vs AHash	1	≈ 0.31 pp.
8. Additional Qualitative Examples	1	≈ 4.15 pp.

• Table 6 · p. 1
• Table 5 · p. 1
• Figure 6 · p. 2
• Figure 5 · p. 2
• Figure 7 · p. 3
• Figure 4 · p. 4
• Figure 8 · p. 5

Argument and organization

1. Problem and contribution

   Leads with concrete duplication and split-leakage findings on named datasets, establishing why apparently strong benchmark performance may be misleading.

2. Argument sequence

   Defines detection and de-duplication before dataset-by-dataset auditing and comparison with another detector.

3. Evidence and verification

   Official and augmented split analyses are separated; the discussion identifies visually blank or no-data regions as possible false positives.

Problem, claim and contribution

Leads with concrete duplication and split-leakage findings on named datasets, establishing why apparently strong benchmark performance may be misleading.

Abstract and Introduction, p. 1 · Main paper · Additional source 2

Argument and section order

Defines detection and de-duplication before dataset-by-dataset auditing and comparison with another detector.

Sections 3–4, pp. 3–7 · Main paper · Additional source 2

Figures, captions and visual explanation

Figure 2 arranges each validation image alongside several training duplicates and retains filenames, making the alleged leakage visually checkable.

Figure 2, p. 6 · Main paper · Additional source 2

Tables, comparisons and evidence

Official and augmented split analyses are separated; the discussion identifies visually blank or no-data regions as possible false positives.

Tables 1–2 and Section 4.2, pp. 4–5 · Main paper · Additional source 2

Appendix and reproducibility

The supplementary gallery explicitly includes false-positive detections on INRIA and SpaceNet, not only the strongest leakage examples.

Supplement Figures 7–8, pp. 4–5 · Main paper · Additional source 2

Clarity and writing conventions

The conclusion names geometric-augmentation dependence as a limitation instead of presenting the detector as invariant to arbitrary transformations.

Section 5, pp. 7–8 · Main paper · Additional source 2

What to reuse—and what not to infer

Transferable lesson: An audit paper should show concrete counterexamples, distinguish detector alarms from confirmed issues, and trace how corrected data change conclusions.

Boundary: Scientific discussion of perceptual hashing is part of this paper's method, not a website fingerprint feature; detected matches still require interpretation, especially uniform/no-data regions.

Apply this lesson using the argument and evidence worksheet.

Inspection record and sources

Checked

2026-09-26

Reading status

Writing-focused manuscript scan + selected visuals inspected

Main text

Writing-oriented scan throughout Sections 1–5, PDF pp. 1–8; references pp. 9–10: abstract/framing, section sequence, figure/table captions, evaluation organization and conclusions; not an exhaustive technical verification.

Appendix / supplement

Writing-oriented supplement scan: Supplement Sections 6–8, pp. 1–5: retraining/overfitting, PHash/AHash comparisons and additional true/false duplicate examples. Video/code assets were not executed or assessed.

Visually inspected PDF pages

6, 4

This is a writing-focused scan of the manuscript and the stated supplementary scope: framing, organization, visual explanation, evidence presentation and wording. It is not a line-by-line proof audit, reproduction of results or exhaustive scientific review.

• Official CVF open-access CVPR 2026 accepted-paper PDF · 10 pages
• Official CVF supplementary PDF · 5 pages