# Few-shot Domain Generalization on Meta-Dataset ImageNet-only v1 (train) Source: [Few-shot Domain Generalization on Meta-Dataset ImageNet-only v1 (train)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:34:17.952Z Evaluation of Few-shot Domain Generalization performance using the training split data subset of Meta-Dataset ImageNet-only v1, reporting specialized metrics across constituent datasets. 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 | Few-shot domain generalization | | Dataset (including any stated split) | Meta-Dataset ImageNet-only v1 (train) | | Metric | Accuracy (ImageNet) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 8 of 8 | | 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 (ImageNet)](): Higher is better; unit: PERCENT. - [Accuracy (Omniglot)](): Higher is better; unit: PERCENT. - [Accuracy (Aircraft)](): Higher is better; unit: PERCENT. - [Accuracy (Birds)](): Higher is better; unit: PERCENT. - [Accuracy (Textures)](): Higher is better; unit: PERCENT. - [Accuracy (Quick Draw)](): Higher is better; unit: PERCENT. - [Accuracy (Fungi)](): Higher is better; unit: PERCENT. - [Accuracy (VGG Flower)](): Higher is better; unit: PERCENT. - [Accuracy (Traffic Sign)](): Higher is better; unit: PERCENT. - [Accuracy (MSCOCO)](): Higher is better; unit: PERCENT. - [Accuracy (MNIST\*)](): Higher is better; unit: PERCENT. - [Accuracy (CIFAR-10\*)](): Higher is better; unit: PERCENT. - [Accuracy (CIFAR-100\*)](): Higher is better; unit: PERCENT. - [Avg Accuracy (Seen)](): Higher is better; unit: PERCENT. - [Avg Accuracy (Unseen w/o \*)](): Higher is better; unit: PERCENT. - [Avg Accuracy (All w/o \*)](): Higher is better; unit: PERCENT. - [Avg Accuracy (Unseen w/ \*)](): Higher is better; unit: PERCENT. - [Avg Accuracy (All w/ \*)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy (ImageNet) | Result date | Report paper | | --- | --- | --- | --- | | GAP + Proto-MAML | 56.66 | Not recorded | 68fa715a1e209131cea50ca5 | | Approximate GAP + Proto-MAML | 56.65 | Not recorded | 68fa715a1e209131cea50ca5 | | GAP + fo-MAML | 56.33 | Not recorded | 68fa715a1e209131cea50ca5 | | Approximate GAP + fo-MAML | 55.34 | Not recorded | 68fa715a1e209131cea50ca5 | | ALFA + Proto-MAML | 52.8 | Not recorded | 68fa715a1e209131cea50ca5 | | ALFA + fo-MAML | 51.09 | Not recorded | 68fa715a1e209131cea50ca5 | | Proto-MAML | 49.53 | Not recorded | 68fa715a1e209131cea50ca5 | | fo-MAML | 45.51 | Not recorded | 68fa715a1e209131cea50ca5 | ### GAP + Proto-MAML Accuracy (ImageNet): 56.66. Result ID: 6991ad693a6c31484909d750. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-18","Training Setting":"ImageNet only"}. This record does not assert independent reproduction. ### Approximate GAP + Proto-MAML Accuracy (ImageNet): 56.65. Result ID: 6991ad693a6c31484909d74e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-18","Training Setting":"ImageNet only"}. This record does not assert independent reproduction. ### GAP + fo-MAML Accuracy (ImageNet): 56.33. Result ID: 6991ad693a6c31484909d74f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-18","Training Setting":"ImageNet only"}. This record does not assert independent reproduction. ### Approximate GAP + fo-MAML Accuracy (ImageNet): 55.34. Result ID: 6991ad693a6c31484909d74d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-18","Training Setting":"ImageNet only"}. This record does not assert independent reproduction. ### ALFA + Proto-MAML Accuracy (ImageNet): 52.8. Result ID: 6991ad693a6c31484909d74c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-18","Training Setting":"ImageNet only"}. This record does not assert independent reproduction. ### ALFA + fo-MAML Accuracy (ImageNet): 51.09. Result ID: 6991ad693a6c31484909d74b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-18","Training Setting":"ImageNet only"}. This record does not assert independent reproduction. ### Proto-MAML Accuracy (ImageNet): 49.53. Result ID: 6991ad693a6c31484909d74a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-18","Training Setting":"ImageNet only"}. This record does not assert independent reproduction. ### fo-MAML Accuracy (ImageNet): 45.51. Result ID: 6991ad693a6c31484909d749. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-18","Training Setting":"ImageNet only"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.