# Image Classification on COVIDx CRX-2 (500 samples) Source: [Image Classification on COVIDx CRX-2 (500 samples)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:51:50.046Z Evaluation of Image Classification performance on the specific 500-sample subset of the COVIDx CRX-2 dataset, reporting mean 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 | Image Classification | | Dataset (including any stated split) | COVIDx CRX-2 (500 samples) | | Metric | Mean Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 14 of 14 | | 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 - [Mean Accuracy](): Higher is better; unit: PERCENT. - [Standard Error](): Lower is better; unit: SCALAR. ## Recorded results | Method | Mean Accuracy | Result date | Report paper | | --- | --- | --- | --- | | LS+WRN | 91.56 | Not recorded | 68fa6d3c1e209131cea38a7e | | LS+WRN | 90.5 | Not recorded | 68fa6d3c1e209131cea38a7e | | S+WRN | 89.05 | Not recorded | 68fa6d3c1e209131cea38a7e | | LS+LL | 88.5 | Not recorded | 68fa6d3c1e209131cea38a7e | | LS+WRN | 88.08 | Not recorded | 68fa6d3c1e209131cea38a7e | | LS+LL | 87.56 | Not recorded | 68fa6d3c1e209131cea38a7e | | LS+WRN | 87.44 | Not recorded | 68fa6d3c1e209131cea38a7e | | S+LL | 87.2 | Not recorded | 68fa6d3c1e209131cea38a7e | | S+WRN | 86.68 | Not recorded | 68fa6d3c1e209131cea38a7e | | LS+LL | 86.45 | Not recorded | 68fa6d3c1e209131cea38a7e | | ResNet-50 | 86.45 | Not recorded | 68fa6d3c1e209131cea38a7e | | WRN-16 | 85.95 | Not recorded | 68fa6d3c1e209131cea38a7e | | LS+LL | 85.64 | Not recorded | 68fa6d3c1e209131cea38a7e | | S+LL | 84.13 | Not recorded | 68fa6d3c1e209131cea38a7e | ### LS+WRN Mean Accuracy: 91.56. Result ID: 698f851f3a6c314849f99ba7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Init.":"TF","Parameterization":"Equivariant"}. This record does not assert independent reproduction. ### LS+WRN Mean Accuracy: 90.5. Result ID: 698f851f3a6c314849f99ba6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Init.":"TF","Parameterization":"Canonical"}. This record does not assert independent reproduction. ### S+WRN Mean Accuracy: 89.05. Result ID: 698f851f3a6c314849f99ba8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Init.":"TF","Parameterization":"Fixed"}. This record does not assert independent reproduction. ### LS+LL Mean Accuracy: 88.5. Result ID: 698f851f3a6c314849f99ba0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Init.":"TF","Parameterization":"Canonical"}. This record does not assert independent reproduction. ### LS+WRN Mean Accuracy: 88.08. Result ID: 698f851f3a6c314849f99ba9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Init.":"Rand","Parameterization":"Canonical"}. This record does not assert independent reproduction. ### LS+LL Mean Accuracy: 87.56. Result ID: 698f851f3a6c314849f99ba1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Init.":"TF","Parameterization":"Equivariant"}. This record does not assert independent reproduction. ### LS+WRN Mean Accuracy: 87.44. Result ID: 698f851f3a6c314849f99baa. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Init.":"Rand","Parameterization":"Equivariant"}. This record does not assert independent reproduction. ### S+LL Mean Accuracy: 87.2. Result ID: 698f851f3a6c314849f99ba2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Init.":"TF","Parameterization":"Fixed"}. This record does not assert independent reproduction. ### S+WRN Mean Accuracy: 86.68. Result ID: 698f851f3a6c314849f99bab. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Init.":"Rand","Parameterization":"Fixed"}. This record does not assert independent reproduction. ### LS+LL Mean Accuracy: 86.45. Result ID: 698f851f3a6c314849f99ba3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Init.":"Rand","Parameterization":"Canonical"}. This record does not assert independent reproduction. ### ResNet-50 Mean Accuracy: 86.45. Result ID: 698f851f3a6c314849f99bad. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### WRN-16 Mean Accuracy: 85.95. Result ID: 698f851f3a6c314849f99bac. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### LS+LL Mean Accuracy: 85.64. Result ID: 698f851f3a6c314849f99ba4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Init.":"Rand","Parameterization":"Equivariant"}. This record does not assert independent reproduction. ### S+LL Mean Accuracy: 84.13. Result ID: 698f851f3a6c314849f99ba5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Init.":"Rand","Parameterization":"Fixed"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.