Detection of Small Objects from UAV Imagery via an Improved Swin Transformer
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Automated detection of small objects such as vehicles in images of complex urban environments taken by unmanned aerial vehicles (UAVs) is one of the most challenging tasks in computer vision and remote sensing communities. Convolutional neural networks (CNNs)-based deep learning models have been widely used to automatically detect objects in UAV images given their high performance. However, their detection accuracy is still unsatisfactory, particularly when it comes to small objects, due to the shortcomings of CNNs. Therefore, in this study, we propose a Swin Transformer-based model that incorporates convolutions with the Swin Transformer to extract more local information, mitigating the problem of small object detection from complex backgrounds in UAV images and further improving the detection accuracy. By using the Swin Transformer, our model leverages both the local feature extraction of convolutions and the global feature modeling of transformers. The framework comprises two primary modules: a Local Context Enhancement (LCE) module and a Residual U-Feature Pyramid Network (RSU-FPN) module. Additionally, it incorporates a loss function that combines L1 loss with Normalized Gaussian Wasserstein Distance. Our experimental results obtained on the UAV Detection and Tracking (UAVDT) dataset indicated that our proposed method increased the average precision (AP) by 21.6%, 22.3% and 25.5% over Cascade Region-based CNN (R-CNN), Faster Region based CNN (R-CNN) with ResNet-50 and with Pyramid Vision Transformer (PVT) B0, and Dynamic R-CNN detectors, respectively, indicating its effectiveness and reliability on small object detection from UAV images.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 it