Optimization of automated garbage recognition model based on ResNet-50 and weakly supervised CNN for sustainable urban development
Bibliographic record
Abstract
In the context of sustainable urban development, effective garbage management plays a crucial role. However, traditional methods encounter limitations in terms of data quality and quantity. The research on automatic garbage image recognition and classification methods based on deep learning has been gaining attention. This study proposes an integrated garbage image recognition and classification method that combines ResNet-50, YOLOv5, and weakly supervised CNN algorithms. The aim is to enhance both the accuracy and efficiency of image recognition, optimize intelligent garbage management, and promote urban sustainable development planning. The ResNet-50 model is employed to extract meaningful features from images and train weakly supervised CNN models for subsequent training and prediction. This enables the analysis of urban environmental development trends and the formulation of planning measures. Through evaluation on four representative public datasets, the proposed method outperforms several traditional algorithms in terms of accuracy, efficiency, and stability in garbage image recognition systems. Notably, on the HGI-30 dataset, the algorithm achieves significant improvements by reducing inference time by over 48.6%, FLOPs by over 46.5%, and MAPE by over 41%. These enhancements greatly enhance the accuracy and robustness of garbage image classification, highlighting the substantial significance of this method in the realms of garbage management and environmental protection. • We integrate different deep learning algorithms to enhance the accuracy and efficiency. • Integration of IoT and communication technologies optimizes the intelligent garbage management. • The method holds significance for waste management and sustainable urban development planning.
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 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| 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".