http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-110414377-B
Outgoing Links
| Predicate | Object |
|---|---|
| classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-24147 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-241 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V20-13 |
| classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62 |
| filingDate | 2019-07-09-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| grantDate | 2020-11-13-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationDate | 2020-11-13-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber | CN-110414377-B |
| titleOfInvention | A scene classification method for remote sensing images based on scale attention network |
| abstract | The invention discloses a remote sensing image scene classification method based on a scale attention network. First, a scene data set is randomly divided into a training set and a test set in proportion; then, the data set is preprocessed, including image scaling and normalization At the same time, input the data set into the attention module for saliency detection, and generate the attention map; then, use the pre-training model to initialize the scale attention network parameters, and use the training set and attention map to fine-tune the scale attention network, save the training Good network model; finally, use the fine-tuned scale attention network to predict the class of the image scene to be classified. The remote sensing image scene classification method based on the scale attention network uses the multi-scale attention map to weight the feature map for many times, and then extracts and fuses the multi-scale image features to generate a feature representation with enhanced discriminant power. achieved better results. |
| priorityDate | 2019-07-09-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
| Predicate | Subject |
|---|---|
| isDiscussedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID456171974 |
Total number of triples: 14.