Leveraging Attention U-Net in Generative Adversarial Networks for Satellite to Map Image Translation
Bibliographic record
Abstract
Generating realistic map images from satellite imagery is a challenging task in computer vision. This paper proposes a novel approach that leverages an attention-based U-Net architecture within a conditional generative adversarial network (cGAN) framework. Spatial and channel-wise attention blocks are integrated within a U-Net architecture to selectively focus the network on translating geospatially salient features. Extensive experiments on the Pix2Pix dataset of satellite and map image pairs demonstrate that our attention-enhanced cGAN model synthesizes maps that are more accurate and realistic than baseline cGAN approaches. Quantitative results show that our model achieves a PSNR of more than 2 dB and a 0.05 higher SSIM compared to cGAN. Furthermore, the FID score is reduced by 15% over the baseline, indicating the enhanced realism of the generated maps. This work provides both quantitative and qualitative results which highlight the merits of using attention to guide the image translation process.
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 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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, 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".