Automated Classification and Change Detection of Remote Sensing Images Based on Convolutional Neural Networks
Bibliographic record
Abstract
In order to better realize the automatic classi ication and change detection of remote sensing images, this paper proposes an automatic remote sensing image classi ication model based on CNN and migration learning, and constructs a remote sensing image change detection model by combining CNN and Transformer network.In the remote sensing image classi ication model, DenseNet network and Inception network are used as the backbone network, combined with the new channel attention module to mine the image features of remote sensing images, and then realize the accurate classi ication of remote sensing images.In the remote sensing image change detection model, the convolution operation of CNN with different sizes of void rate and expansion rate is utilized to better guide the feature map to focus on local information.Combined with the dynamic deformable Transformer to provide more accurate remote sensing image location information and detail information, to reduce the impact of background interference on remote sensing image change detection, and to improve the model's ability to recognize the target of remote sensing images.The parameter count and loating-point computation of the remote sensing image classi ication model are 7.69MB and 1.89GB, respectively, which are smaller than the parameter count and loating-point computation of the single network model.The RSICD models mF1 and mIoU are 1.66% and 0.58% higher than the optimal ones.Through the effective integration of convolutional neural networks and many different types of deep learning techniques, automated classi ication and change detection of remote sensing images can be realized.
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) | 0.000 | 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 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".