# SAR Image Classification on FUSAR-Ship (test) Source: [SAR Image Classification on FUSAR-Ship (test)]() Collection index: [llms.txt]() Data updated: 2026-04-03T08:49:00.369Z Evaluation of SAR Image Classification performance specifically on the test split of the FUSAR-Ship dataset, measured using Accuracy. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | SAR Image Classification | | Dataset (including any stated split) | FUSAR-Ship (test) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 12 of 12 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Light-ResKAN | 93.01 | Not recorded | 69cf49b10636e5bf4afcdaff | | ResKAGNet | 91.58 | Not recorded | 69cf49b10636e5bf4afcdaff | | VGG16 | 90.73 | Not recorded | 69cf49b10636e5bf4afcdaff | | AlexNet | 89.41 | Not recorded | 69cf49b10636e5bf4afcdaff | | MACN | 89.15 | Not recorded | 69cf49b10636e5bf4afcdaff | | ResNet50 | 86.71 | Not recorded | 69cf49b10636e5bf4afcdaff | | ResNet18 | 83.54 | Not recorded | 69cf49b10636e5bf4afcdaff | | SpectralKAN | 81.21 | Not recorded | 69cf49b10636e5bf4afcdaff | | ASANet | 78.84 | Not recorded | 69cf49b10636e5bf4afcdaff | | Cross-HL | 78.06 | Not recorded | 69cf49b10636e5bf4afcdaff | | ConvNeXt | 77.86 | Not recorded | 69cf49b10636e5bf4afcdaff | | WaveKAN | 70.61 | Not recorded | 69cf49b10636e5bf4afcdaff | ### Light-ResKAN Accuracy: 93.01. Result ID: 69cf7ede47f34ce924b97981. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Year":"2025","Pars. (M)":"0.82","Size (MB)":"2.41","FLOPs (G)":"0.97","Test time (ms)":"58.74"}. This record does not assert independent reproduction. ### ResKAGNet Accuracy: 91.58. Result ID: 69cf7ede47f34ce924b97980. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Year":"2024","Pars. (M)":"0.90","Size (MB)":"3.58","FLOPs (G)":"1.29","Test time (ms)":"51.36"}. This record does not assert independent reproduction. ### VGG16 Accuracy: 90.73. Result ID: 69cf7ede47f34ce924b97977. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Year":"2015","Pars. (M)":"134.30","Size (MB)":"537.21","FLOPs (G)":"80.37","Test time (ms)":"43.72"}. This record does not assert independent reproduction. ### AlexNet Accuracy: 89.41. Result ID: 69cf7ede47f34ce924b97976. [Reporting paper]() Recorded evaluation configuration: {"Year":"2012","Pars. (M)":"57.04","Size (MB)":"228.18","FLOPs (G)":"3.71","Test time (ms)":"30.32"}. This record does not assert independent reproduction. ### MACN Accuracy: 89.15. Result ID: 69cf7ede47f34ce924b9797b. [Reporting paper]() Recorded evaluation configuration: {"Year":"2022","Pars. (M)":"0.05","Size (MB)":"0.16","FLOPs (G)":"12.40","Test time (ms)":"296.75"}. This record does not assert independent reproduction. ### ResNet50 Accuracy: 86.71. Result ID: 69cf7ede47f34ce924b97979. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Year":"2016","Pars. (M)":"23.53","Size (MB)":"94.11","FLOPs (G)":"21.35","Test time (ms)":"32.93"}. This record does not assert independent reproduction. ### ResNet18 Accuracy: 83.54. Result ID: 69cf7ede47f34ce924b97978. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Year":"2016","Pars. (M)":"11.18","Size (MB)":"44.73","FLOPs (G)":"9.51","Test time (ms)":"32.41"}. This record does not assert independent reproduction. ### SpectralKAN Accuracy: 81.21. Result ID: 69cf7ede47f34ce924b9797e. [Reporting paper]() Recorded evaluation configuration: {"Year":"2024","Pars. (M)":"0.51","Size (MB)":"2.02","FLOPs (G)":"0.41","Test time (ms)":"48.02"}. This record does not assert independent reproduction. ### ASANet Accuracy: 78.84. Result ID: 69cf7ede47f34ce924b9797d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Year":"2024","Pars. (M)":"27.95","Size (MB)":"111.28","FLOPs (G)":"46.82","Test time (ms)":"47.23"}. This record does not assert independent reproduction. ### Cross-HL Accuracy: 78.06. Result ID: 69cf7ede47f34ce924b9797c. [Reporting paper]() Recorded evaluation configuration: {"Year":"2024","Pars. (M)":"0.52","Size (MB)":"2.06","FLOPs (G)":"0.22","Test time (ms)":"35.64"}. This record does not assert independent reproduction. ### ConvNeXt Accuracy: 77.86. Result ID: 69cf7ede47f34ce924b9797a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Year":"2022","Pars. (M)":"87.58","Size (MB)":"350.23","FLOPs (G)":"80.53","Test time (ms)":"53.25"}. This record does not assert independent reproduction. ### WaveKAN Accuracy: 70.61. Result ID: 69cf7ede47f34ce924b9797f. [Reporting paper]() Recorded evaluation configuration: {"Year":"2024","Pars. (M)":"4.82","Size (MB)":"19.23","FLOPs (G)":"0.40","Test time (ms)":"57.14"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.