Small Target Detection Methods in Complex Scenes
Bibliographic record
Abstract
Small target detection is of great significance in military and civilian fields, so the problems of small target aggregation and scale diversity under scene complexity, this paper proposes a small target detection method under complex scenes for small target aggregation and scale diversity under scene complexity. Firstly, we design a multiscale grouping efficient convolution module, Multi-ScaleGroupEfficientConv, to replace part of the C2f module, so as to extract multiscale features efficiently; secondly, we construct a feature pyramid network for small targets and construct a CSP-OmniKernel feature fusion module based on the idea of CSP and OmniKernel to retain the information of small targets to a greater extent. The intent is to retain the information of small targets and improve the target detection ability. Finally, on the VisDrone2019 dataset, comparison experiments are conducted with mainstream algorithms, and the experimental results show that the method in this paper improves 1.2%, 2.1%, 2.6%, and 1.3% in the detection rate, recall rate, mAP50, and mAP50:95, respectively, in comparison with the original yolov8n, and the model size and the number of parameters are only 6.1MB and 3.02M, which are better than other mainstream methods.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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".