# Image Classification on ImageNet OOD Transfer Suite (CUB, Cars, Aircrafts, Pets) LT (test) Source: [Image Classification on ImageNet OOD Transfer Suite (CUB, Cars, Aircrafts, Pets) LT (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:38:53.048Z Evaluation of Image Classification performance using a transfer learning setup across the OOD/LT subsets CUB, Cars, Aircrafts, and Pets derived from the ImageNet suite, measured on the test split. 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) | ImageNet OOD Transfer Suite (CUB, Cars, Aircrafts, Pets) LT (test) | | Metric | CUB Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 7 of 7 | | 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. - [Aircrafts Accuracy](): Higher is better; unit: PERCENT. - [Pets Accuracy](): Higher is better; unit: PERCENT. - [Avg. Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | CUB Accuracy | Result date | Report paper | | --- | --- | --- | --- | | SimSiam+rwSAM | 70.7 | Not recorded | 68fa6c961e209131cea34acd | | SimSiam, balanced | 70.5 | Not recorded | 68fa6c961e209131cea34acd | | MoCo v2+rwSAM | 70.3 | Not recorded | 68fa6c961e209131cea34acd | | SimSiam | 70 | Not recorded | 68fa6c961e209131cea34acd | | MoCo v2 | 69.9 | Not recorded | 68fa6c961e209131cea34acd | | MoCo v2+SAM | 69.9 | Not recorded | 68fa6c961e209131cea34acd | | MoCo v2, balanced | 69.8 | Not recorded | 68fa6c961e209131cea34acd | ### SimSiam+rwSAM CUB Accuracy: 70.7. Result ID: 698f22c83a6c314849f61c8f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pre-training Dataset":"ImageNet-LT","Evaluation Protocol":"fine-tuning","Regularization":"rwSAM"}. This record does not assert independent reproduction. ### SimSiam, balanced CUB Accuracy: 70.5. Result ID: 698f22c83a6c314849f61c8e. [Reporting paper]() Recorded evaluation configuration: {"Pre-training Dataset":"Balanced dataset (subset of ImageNet)","Evaluation Protocol":"fine-tuning"}. This record does not assert independent reproduction. ### MoCo v2+rwSAM CUB Accuracy: 70.3. Result ID: 698f22c83a6c314849f61c8c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pre-training Dataset":"ImageNet-LT","Evaluation Protocol":"fine-tuning","Regularization":"rwSAM"}. This record does not assert independent reproduction. ### SimSiam CUB Accuracy: 70. Result ID: 698f22c83a6c314849f61c8d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-training Dataset":"ImageNet-LT","Evaluation Protocol":"fine-tuning"}. This record does not assert independent reproduction. ### MoCo v2 CUB Accuracy: 69.9. Result ID: 698f22c83a6c314849f61c89. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pre-training Dataset":"ImageNet-LT","Evaluation Protocol":"fine-tuning"}. This record does not assert independent reproduction. ### MoCo v2+SAM CUB Accuracy: 69.9. Result ID: 698f22c83a6c314849f61c8a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pre-training Dataset":"ImageNet-LT","Evaluation Protocol":"fine-tuning","Regularization":"SAM"}. This record does not assert independent reproduction. ### MoCo v2, balanced CUB Accuracy: 69.8. Result ID: 698f22c83a6c314849f61c8b. [Reporting paper]() Recorded evaluation configuration: {"Pre-training Dataset":"Balanced dataset (subset of ImageNet)","Evaluation Protocol":"fine-tuning"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.