A Novel Unsupervised Change Detection Network Based on Legendre Multiwavelet Theory and Depthwise Convolution With Channel Gating
Bibliographic record
Abstract
Synthetic Aperture Radar (SAR) image change detection is a fundamental task in remote sensing image analysis. However, the poor discriminability of image change features and the low detectability in complex change regions, such as farmland, and riverbanks, are challenging for unsupervised learning methods. To address these challenges, this paper proposes a novel unsupervised learning network architecture based on Legendre Multi-wavelet theory and Depthwise Convolution with Channel Gating (LWDCG). In LWDCG, we first design an Legendre Wavelet Channel Attention module leveraging LW transform to decompose SAR image into multi-wavelet multi-scale representations and combining with a channel attention mechanism to enhance discriminative feature learning. Then, we employ a hierarchical strategy integrating with Possibilistic C-Means clustering to enhance clustering performance. Furthermore, we introduce a DCG module integrating depthwise separable convolution with a gating mechanism. This design enables both efficient feature extraction and dynamic filtering of change-sensitive features, significantly improving detection performance in complex regions. Finally, Extensive experiments on three public SAR datasets (Sulzberger, Ottawa, and Yellow River) demonstrate the effectiveness of our approach, achieving percentage of correct classification (PCC) of 98.88%, 98.46%, and 95.73%, respectively. The results validate the rationality and superiority of the proposed network architecture in SAR change detection tasks.
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) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".