E2 Net: Efficient and Effective Dense Pedestrian Detection Network Based on YOLOv8
Bibliographic record
Abstract
The goal of dense pedestrian detection is to accurately identify and locate pedestrians in crowded scenes. The majority of available dense pedestrian detection algorithms are built on a two-stage framework. The two-stage framework generally transforms the target detection task into a regression task by selecting candidate regions. However, two-stage-based approaches have issues with high computational complexity and subpar real-time performance since they necessitate several region suggestions and feature extraction operations. By executing prediction and regression operations directly on the feature map and skipping region suggestion and multi-stage processing, YOLOv8, as a single-stage detection approach, may substantially decrease computational complexity and increase real-time performance. However, it still has shortcomings in small-scale pedestrian detection and occlusion processing. To solve this problem, we propose an efficient and effective dense pedestrian detection method based on YOLOv8, called E2 Net. We introduce an efficient convolution operator, Partial Convolution (PConv), to reduce computational redundancy and memory consumption. Also, we apply PConv to the FasterNet architecture to improve feature extraction efficiency while maintaining performance, enabling efficient spatial feature extraction on multiple devices. In addition, we introduce a novel loss optimization scheme to reduce small-scale pedestrian misses and incorporate a weighted bi-directional feature pyramid network (BiFPN) to achieve a flexible multi-scale feature fusion algorithm with content awareness. Through extensive experiments, it has been verified that E2 Net has higher accuracy and efficiency on dense pedestrian detection tasks than existing state-of-the-art algorithms.
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 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.003 | 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".