# Continual Fine-Tuning on ImageNet-A N = 20 Source: [Continual Fine-Tuning on ImageNet-A N = 20]() Collection index: [llms.txt]() Data updated: 2026-06-29T07:31:55.546Z Evaluation of model performance using Continual Fine-Tuning methodology on the specific subset ImageNet-A (N=20), tracking accuracy, forgetting, and adapter usage. 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 | Continual Fine-Tuning | | Dataset (including any stated split) | ImageNet-A N = 20 | | Metric | Average Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 6 of 6 | | 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 - [Average Accuracy](): Higher is better; unit: PERCENT. - [Forgetting](): Lower is better; unit: PERCENT. - [Number of Active Adapters](): Higher is better; unit: SCALAR. ## Recorded results | Method | Average Accuracy | Result date | Report paper | | --- | --- | --- | --- | | LITELORA | 66.53 | Not recorded | 6a41fc30206542251d7ccc56 | | SD-LoRA | 66.3 | Not recorded | 6a41fc30206542251d7ccc56 | | LITELORA | 65.75 | Not recorded | 6a41fc30206542251d7ccc56 | | SD-LoRA | 64.85 | Not recorded | 6a41fc30206542251d7ccc56 | | LITELORA | 63.64 | Not recorded | 6a41fc30206542251d7ccc56 | | SD-LoRA | 62.08 | Not recorded | 6a41fc30206542251d7ccc56 | ### LITELORA Average Accuracy: 66.53. Result ID: 6a421f63fbc373592c8763d2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Task Order":"Order 2"}. This record does not assert independent reproduction. ### SD-LoRA Average Accuracy: 66.3. Result ID: 6a421f63fbc373592c8763cf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Task Order":"Order 2"}. This record does not assert independent reproduction. ### LITELORA Average Accuracy: 65.75. Result ID: 6a421f63fbc373592c8763d1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Task Order":"Order 1"}. This record does not assert independent reproduction. ### SD-LoRA Average Accuracy: 64.85. Result ID: 6a421f63fbc373592c8763ce. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Task Order":"Order 1"}. This record does not assert independent reproduction. ### LITELORA Average Accuracy: 63.64. Result ID: 6a421f63fbc373592c8763d3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Task Order":"Order 3"}. This record does not assert independent reproduction. ### SD-LoRA Average Accuracy: 62.08. Result ID: 6a421f63fbc373592c8763d0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Task Order":"Order 3"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.