# Image Classification on BSCD-FSL 8 Domains (test) Source: [Image Classification on BSCD-FSL 8 Domains (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:38:53.032Z Evaluation of Image Classification performance across 8 target domains (CUB, Cars, Plantae, Places, CropDisease, EuroSAT, ISIC, ChestX) on the test split, reporting per-domain results and an average. 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 | Image Classification | | Dataset (including any stated split) | BSCD-FSL 8 target domains: CUB, Cars, Plantae, Places, CropDisease, EuroSAT, ISIC, ChestX standard (test) | | Metric | CUB Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 13 of 13 | | 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 - [CUB Accuracy](): Higher is better; unit: PERCENT. - [Cars Accuracy](): Higher is better; unit: PERCENT. - [Plantae Accuracy](): Higher is better; unit: PERCENT. - [Places Accuracy](): Higher is better; unit: PERCENT. - [CropDisease Accuracy](): Higher is better; unit: PERCENT. - [EuroSAT Accuracy](): Higher is better; unit: PERCENT. - [ISIC Accuracy](): Higher is better; unit: PERCENT. - [ChestX Accuracy](): Higher is better; unit: PERCENT. - [Average Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | CUB Accuracy | Result date | Report paper | | --- | --- | --- | --- | | ConFT | 70.53 | Not recorded | 68fa6c0e1e209131cea31bf0 | | NSAE(CE+CE) | 68.51 | Not recorded | 68fa6c0e1e209131cea31bf0 | | RDC-FT | 67.77 | Not recorded | 68fa6c0e1e209131cea31bf0 | | TPN+ATA | 65.31 | Not recorded | 68fa6c0e1e209131cea31bf0 | | GNN+FT | 64.97 | Not recorded | 68fa6c0e1e209131cea31bf0 | | Fine-tuning | 63.76 | Not recorded | 68fa6c0e1e209131cea31bf0 | | GNN+LRP | 62.86 | Not recorded | 68fa6c0e1e209131cea31bf0 | | RDC-FT | 51.2 | Not recorded | 68fa6c0e1e209131cea31bf0 | | TPN+ATA | 50.26 | Not recorded | 68fa6c0e1e209131cea31bf0 | | ConFT | 45.57 | Not recorded | 68fa6c0e1e209131cea31bf0 | | GNN+FT | 45.5 | Not recorded | 68fa6c0e1e209131cea31bf0 | | GNN+LRP | 43.89 | Not recorded | 68fa6c0e1e209131cea31bf0 | | Fine-tuning | 43.53 | Not recorded | 68fa6c0e1e209131cea31bf0 | ### ConFT CUB Accuracy: 70.53. Result ID: 698ebf6affc3901de0a0b05a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet10","N-way":5,"K-shot":5,"Fine-tuning in the target domain":true,"Result source":"Reproduced using official code"}. This record does not assert independent reproduction. ### NSAE(CE+CE) CUB Accuracy: 68.51. Result ID: 698ebf6affc3901de0a0b05b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet10","N-way":5,"K-shot":5}. This record does not assert independent reproduction. ### RDC-FT CUB Accuracy: 67.77. Result ID: 698ebf6affc3901de0a0b05c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet10","N-way":5,"K-shot":5,"Use of labeled support and unlabeled query data":true}. This record does not assert independent reproduction. ### TPN+ATA CUB Accuracy: 65.31. Result ID: 698ebf6affc3901de0a0b058. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet10","N-way":5,"K-shot":5,"Use of labeled support and unlabeled query data":true}. This record does not assert independent reproduction. ### GNN+FT CUB Accuracy: 64.97. Result ID: 698ebf6affc3901de0a0b056. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet10","N-way":5,"K-shot":5,"Reported in \[46\]":true}. This record does not assert independent reproduction. ### Fine-tuning CUB Accuracy: 63.76. Result ID: 698ebf6affc3901de0a0b059. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet10","N-way":5,"K-shot":5,"Fine-tuning in the target domain":true,"Reported in \[46\]":true}. This record does not assert independent reproduction. ### GNN+LRP CUB Accuracy: 62.86. Result ID: 698ebf6affc3901de0a0b057. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet10","N-way":5,"K-shot":5,"Reported in \[46\]":true}. This record does not assert independent reproduction. ### RDC-FT CUB Accuracy: 51.2. Result ID: 698ebf6affc3901de0a0b055. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet10","N-way":5,"K-shot":1,"Use of labeled support and unlabeled query data":true}. This record does not assert independent reproduction. ### TPN+ATA CUB Accuracy: 50.26. Result ID: 698ebf6affc3901de0a0b052. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet10","N-way":5,"K-shot":1,"Use of labeled support and unlabeled query data":true}. This record does not assert independent reproduction. ### ConFT CUB Accuracy: 45.57. Result ID: 698ebf6affc3901de0a0b054. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet10","N-way":5,"K-shot":1,"Fine-tuning in the target domain":true,"Result source":"Reproduced using official code"}. This record does not assert independent reproduction. ### GNN+FT CUB Accuracy: 45.5. Result ID: 698ebf6affc3901de0a0b050. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet10","N-way":5,"K-shot":1,"Reported in \[46\]":true}. This record does not assert independent reproduction. ### GNN+LRP CUB Accuracy: 43.89. Result ID: 698ebf6affc3901de0a0b051. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet10","N-way":5,"K-shot":1,"Reported in \[46\]":true}. This record does not assert independent reproduction. ### Fine-tuning CUB Accuracy: 43.53. Result ID: 698ebf6affc3901de0a0b053. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet10","N-way":5,"K-shot":1,"Fine-tuning in the target domain":true,"Reported in \[46\]":true}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.