A study of enhancement strategies for artificial intelligence-based automated design tools in complex design tasks
Bibliographic record
Abstract
With the important achievements of AI team in the application of diffusion model, automated generation demonstrates its stability, realism and accuracy in text-guided image generation design.In this paper, the automated design generation based on the diffusion model is divided into two processes: forward diffusion and reverse generation.The stable diffusion model is constructed from three parts: self-encoder, U-Net network structure, and text encoder, and the ControlNet control architecture is used to realize the control of the diffusion model to learn a specific task.The model is pre-trained using a combination of three functions: perceptual loss, adversarial loss, and cyclic consistency loss.The LoRA algorithm is added to the U-Net layer of the Stable diffusion model to realize the design task function enhancement of the stable diffusion model.The application effect of the improved Stable diffusion model is analyzed through comparative experiments.The experimental results show that the CLIP Score interval of this paper's model is between 20 and 32.5, while the LPIPS is between 0.1 and 0.6, and the kernel density centroid is (24.85,0.4), which means that the proposed method in this paper meets the design requirements with higher fidelity while accomplishing the image design task.In the design images generated by automation, in terms of visual logic rationality, the structural proportions, line contours, light and shadow and picture hierarchical relationships of the generated images perform well, with the evaluation results of 3.258, 3.564, 3.058, 3.615, respectively, which indicates that the design images generated by automation using the model have a strong richness.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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 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".