Efficient Object Detection with an Optimized YOLOv8x Model
Bibliographic record
Abstract
This study developed an efficient object detection model for indoor environments, addressing common challenges such as occlusions, varying lighting, and cluttered scenes. We evaluated several YOLOv8 variants—ranging from nano to extra-large—and introduced an optimized YOLOv8x model. Our approach combines structured pruning, quantization-aware training, and advanced data preprocessing techniques, including augmentation and noise reduction, to improve model performance while reducing computational demands. The models were developed and evaluated using a carefully selected indoor object detection dataset featuring ten common categories. Performance was measured through key metrics like precision, recall, and mean average precision (mAP). Among them, the fine-tuned YOLOv8x clearly outshined the baseline models, reaching a training precision of 0.577, a recall of 0.572, and an mAP@0.50 of 0.537. When tested on new data, it demonstrated even better generalization, delivering a precision of 0.502, a recall of 0.528, and an mAP@0.50 of 0.480—proving robustness and reliability in real-world scenarios. These results demonstrate that pruning and quantization can significantly reduce model complexity without sacrificing accuracy, which helps to detect indoor objects. In essence, it is optimized for indoor object detection, offering promising applications in smart environments, surveillance, and robotics.
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 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| 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 | 0.001 |
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".