Benchmarking Few-Shot Learning Techniques for Steel Surface Defect Detection
Bibliographic record
Abstract
Steel surface defect detection is crucial for industrial quality control, but acquiring sufficient labeled data for all types of defects remains a challenge. Few-Shot Learning (FSL) offers promising solutions by enabling models to learn from limited examples. This paper presents an investigation of recent FSL implementation strategies specifically applied to steel defect detection, with a focus on methods evaluated on the widely used NEU-DET dataset. We categorize and compare different approaches based on their pre-training and fine-tuning implementations like cross-domain transfer (CDT), in-domain self-supervised pre-training with full or novel-only fine-tuning (ISS-FFT, ISS-NFT), and in-domain supervised pre-training with novel-only fine-tuning (IS-NFT). Furthermore, we introduce and evaluate SSL-YOLO, a method integrating contrastive self-supervised pre-training with a YOLOv8 detector, across these implementation scenarios. This work aims to consolidate current strategies and provide insights into the landscape of few-shot steel defect detection, highlighting both specialized techniques and the performance achievable with effective methods like SSL-YOLO.
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 | 0.003 | 0.006 |
| Meta-epidemiology (narrow) | 0.002 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.003 | 0.002 |
| 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".