Symbol Spotting on Digital Architectural Floor Plans Using a Deep\n Learning-based Framework
Bibliographic record
Abstract
This papers focuses on symbol spotting on real-world digital architectural\nfloor plans with a deep learning (DL)-based framework. Traditional on-the-fly\nsymbol spotting methods are unable to address the semantic challenge of\ngraphical notation variability, i.e. low intra-class symbol similarity, an\nissue that is particularly important in architectural floor plan analysis. The\npresence of occlusion and clutter, characteristic of real-world plans, along\nwith a varying graphical symbol complexity from almost trivial to highly\ncomplex, also pose challenges to existing spotting methods. In this paper, we\naddress all of the above issues by leveraging recent advances in DL and\nadapting an object detection framework based on the You-Only-Look-Once (YOLO)\narchitecture. We propose a training strategy based on tiles, avoiding many\nissues particular to DL-based object detection networks related to the relative\nsmall size of symbols compared to entire floor plans, aspect ratios, and data\naugmentation. Experiments on real-world floor plans demonstrate that our method\nsuccessfully detects architectural symbols with low intra-class similarity and\nof variable graphical complexity, even in the presence of heavy occlusion and\nclutter. Additional experiments on the public SESYD dataset confirm that our\nproposed approach can deal with various degradation and noise levels and\noutperforms other symbol spotting methods.\n
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".