http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-111444939-B
Outgoing Links
| Predicate | Object |
|---|---|
| classificationCPCAdditional | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V2201-07 |
| classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-24 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06Q50-06 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-253 |
| classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V10-80 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06Q50-06 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V10-764 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V10-82 |
| filingDate | 2020-02-19-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| grantDate | 2022-06-28-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationDate | 2022-06-28-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber | CN-111444939-B |
| titleOfInvention | Small-scale equipment component detection method based on weakly supervised collaborative learning in open scenarios in the power field |
| abstract | The detection method of small-scale equipment parts based on weakly supervised collaborative learning in the open scene of the power field, based on the characteristics of small objects of equipment parts, uses the feature pyramid to fuse shallow features and deep features to obtain richer information. When the extracted multi-scale features are input to the candidate region generation network, candidate regions with different scale features will be generated, and the processing range of the strong and weak supervised learning network is divided according to the scale of the candidate region, so as to give full play to the strong supervision sub-network. Synergy between high-performance and weakly supervised subnetworks. And to a large extent, the time cost is reduced, and the balance between efficiency and precision is done. At the same time, the present invention utilizes a detection framework different from the classical Faster R-CNN model to detect the target, thereby simultaneously improving the accuracy and speed of small target detection. |
| priorityDate | 2020-02-19-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Total number of triples: 25.