Multiagent Detection System Based on Spatial Adaptive Feature Aggregation
Bibliographic record
Abstract
Detection systems based on computer vision play important roles in Large-Scale Multiagent Systems. In particular, it can automatically locate and identify key objects and enhance intelligent collaboration and coordination among multiple agents. However, classification and localization in object detection may produce inconsistent prediction results due to different learning focus. Therefore, we propose a Spatial Decoupling and Boundary Feature Aggregation Network (SDBA-Net) to achieve spatial decoupling and task alignment. SDBA-Net includes a spatially sensitive region-aware module (SSRM) and a boundary feature aggregation module (BFAM). SSRM predicts sensitive regions for each task while minimizing computational cost. BFAM extracts valuable boundary features within sensitive regions and aligns them with corresponding anchors. These two modules are combined to spatially decouple and align the features of two tasks. In addition, a significance dependency complementary module (SDCM) is introduced. It enables SSRM to quickly adjust the sensitive region of the classification task to the significant feature region. Experiments are conducted on a large-scale complex real-world dataset MS COCO (Lin et al., 2014). The results show that SDBA-Net achieves better results than the baselines. Using the ResNet-50 backbone, our method improves the average precision (AP) of the single-stage detector VFNet by 1.0 point (from 41.3 to 42.3). In particular, when using the Res2Net-101-DCN backbone, SDBA-Net achieves an AP of 51.8 on the MS COCO test-dev.
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 | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".