Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386420705> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W4386420705 endingPage "4321" @default.
- W4386420705 startingPage "4321" @default.
- W4386420705 abstract "With the exploration of outer space, the number of space targets has increased dramatically, while the pressures of space situational awareness have also increased. Among them, spacecraft recognition is the foundation and a critical step in space situational awareness. However, unlike natural images that can be easily captured using low-cost devices, space targets can suffer from motion blurring, overexposure, and excessive dragging at the time of capture, which greatly affects the quality of the images and reduces the number of effective images. To this end, specialized or sufficiently versatile techniques are required, with dataset diversity playing a key role in enabling algorithms to categorize previously unseen spacecraft and perform multiple tasks. In this paper, we propose a joint dataset formulation to increase diversity. Our approach involves reformulating two local processes to condition the Conditional Neural Adaptive Processes, which results in global feature resampling schemes to adapt a pre-trained embedding function to be task-specific. Specifically, we employ variational resampling to category-wise auxiliary features, adding a generative constraint to amortize task-specific parameters. We also develop a neural process variational inference to encode representation, using grid density for conditioning. Our evaluation of the BUAA dataset shows promising results, with no-training performance close to a specifically designed learner and an accuracy rate of 98.2% on unseen categories during the joint training session. Further experiments on the Meta-dataset benchmark demonstrate at least a 4.6% out-of-distribution improvement compared to the baseline conditional models. Both dataset evaluations indicate the effectiveness of exploiting dataset diversity in few-shot feature adaptation. Our proposal offers a versatile solution for tasks across domains." @default.
- W4386420705 created "2023-09-05" @default.
- W4386420705 creator A5008082931 @default.
- W4386420705 creator A5010913270 @default.
- W4386420705 creator A5011324535 @default.
- W4386420705 creator A5016802132 @default.
- W4386420705 date "2023-09-01" @default.
- W4386420705 modified "2023-09-27" @default.
- W4386420705 title "Generalizing Spacecraft Recognition via Diversifying Few-Shot Datasets in a Joint Trained Likelihood" @default.
- W4386420705 cites W1494192115 @default.
- W4386420705 cites W1861492603 @default.
- W4386420705 cites W2117539524 @default.
- W4386420705 cites W2120287764 @default.
- W4386420705 cites W2742605454 @default.
- W4386420705 cites W2760103357 @default.
- W4386420705 cites W2998676925 @default.
- W4386420705 cites W3034587791 @default.
- W4386420705 cites W3122279293 @default.
- W4386420705 cites W3136670918 @default.
- W4386420705 cites W3142729297 @default.
- W4386420705 cites W3181682259 @default.
- W4386420705 cites W3215694718 @default.
- W4386420705 cites W4200265866 @default.
- W4386420705 cites W4206496144 @default.
- W4386420705 cites W4211049957 @default.
- W4386420705 cites W4304775353 @default.
- W4386420705 cites W4309287962 @default.
- W4386420705 cites W4312235843 @default.
- W4386420705 cites W4313546641 @default.
- W4386420705 cites W4317436033 @default.
- W4386420705 doi "https://doi.org/10.3390/rs15174321" @default.
- W4386420705 hasPublicationYear "2023" @default.
- W4386420705 type Work @default.
- W4386420705 citedByCount "0" @default.
- W4386420705 crossrefType "journal-article" @default.
- W4386420705 hasAuthorship W4386420705A5008082931 @default.
- W4386420705 hasAuthorship W4386420705A5010913270 @default.
- W4386420705 hasAuthorship W4386420705A5011324535 @default.
- W4386420705 hasAuthorship W4386420705A5016802132 @default.
- W4386420705 hasBestOaLocation W43864207051 @default.
- W4386420705 hasConcept C119857082 @default.
- W4386420705 hasConcept C127413603 @default.
- W4386420705 hasConcept C13280743 @default.
- W4386420705 hasConcept C145804949 @default.
- W4386420705 hasConcept C146978453 @default.
- W4386420705 hasConcept C153180895 @default.
- W4386420705 hasConcept C154945302 @default.
- W4386420705 hasConcept C185798385 @default.
- W4386420705 hasConcept C187691185 @default.
- W4386420705 hasConcept C205649164 @default.
- W4386420705 hasConcept C2524010 @default.
- W4386420705 hasConcept C2776214188 @default.
- W4386420705 hasConcept C33923547 @default.
- W4386420705 hasConcept C41008148 @default.
- W4386420705 hasConcept C83665646 @default.
- W4386420705 hasConceptScore W4386420705C119857082 @default.
- W4386420705 hasConceptScore W4386420705C127413603 @default.
- W4386420705 hasConceptScore W4386420705C13280743 @default.
- W4386420705 hasConceptScore W4386420705C145804949 @default.
- W4386420705 hasConceptScore W4386420705C146978453 @default.
- W4386420705 hasConceptScore W4386420705C153180895 @default.
- W4386420705 hasConceptScore W4386420705C154945302 @default.
- W4386420705 hasConceptScore W4386420705C185798385 @default.
- W4386420705 hasConceptScore W4386420705C187691185 @default.
- W4386420705 hasConceptScore W4386420705C205649164 @default.
- W4386420705 hasConceptScore W4386420705C2524010 @default.
- W4386420705 hasConceptScore W4386420705C2776214188 @default.
- W4386420705 hasConceptScore W4386420705C33923547 @default.
- W4386420705 hasConceptScore W4386420705C41008148 @default.
- W4386420705 hasConceptScore W4386420705C83665646 @default.
- W4386420705 hasFunder F4320335787 @default.
- W4386420705 hasIssue "17" @default.
- W4386420705 hasLocation W43864207051 @default.
- W4386420705 hasOpenAccess W4386420705 @default.
- W4386420705 hasPrimaryLocation W43864207051 @default.
- W4386420705 hasRelatedWork W2055384367 @default.
- W4386420705 hasRelatedWork W2060018656 @default.
- W4386420705 hasRelatedWork W2081734071 @default.
- W4386420705 hasRelatedWork W2293915134 @default.
- W4386420705 hasRelatedWork W2405477502 @default.
- W4386420705 hasRelatedWork W2543670224 @default.
- W4386420705 hasRelatedWork W3047965787 @default.
- W4386420705 hasRelatedWork W377926767 @default.
- W4386420705 hasRelatedWork W2137598809 @default.
- W4386420705 hasRelatedWork W2187500075 @default.
- W4386420705 hasVolume "15" @default.
- W4386420705 isParatext "false" @default.
- W4386420705 isRetracted "false" @default.
- W4386420705 workType "article" @default.