# Image Classification on ImageNet 1k (train) - Epoch Progression Metrics Source: [Image Classification on ImageNet 1k (train) - Epoch Progression Metrics]() Collection index: [llms.txt]() Data updated: 2026-03-16T08:59:07.356Z Evaluation of Image Classification performance on the training split of the ImageNet 1k dataset, specifically tracking accuracy metrics achieved at defined training milestones (epochs). 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 1k (train) | | Metric | Accuracy @ 100 Epochs | | 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 @ 100 Epochs](): Higher is better; unit: PERCENT. - [Accuracy @ 200 Epochs](): Higher is better; unit: PERCENT. - [Accuracy @ 400 Epochs](): Higher is better; unit: PERCENT. - [Accuracy @ 800 Epochs](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy @ 100 Epochs | Result date | Report paper | | --- | --- | --- | --- | | Matrix-SSL | 69.2 | Not recorded | 69b78e590636e5bf4afbda06 | | IE-CL | 68.3 | Not recorded | 69b78e590636e5bf4afbda06 | | SimSiam | 68.1 | Not recorded | 69b78e590636e5bf4afbda06 | | MoCo-v2 | 67.4 | Not recorded | 69b78e590636e5bf4afbda06 | | SimCLR | 66.5 | Not recorded | 69b78e590636e5bf4afbda06 | | SwAV | 66.5 | Not recorded | 69b78e590636e5bf4afbda06 | | NNCLR | 65.4 | Not recorded | 69b78e590636e5bf4afbda06 | | All4One | 65.4 | Not recorded | 69b78e590636e5bf4afbda06 | ### Matrix-SSL Accuracy @ 100 Epochs: 69.2. Result ID: 69b7c54347f34ce9249f8bc0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Batch Size":"512","Evaluation Protocol":"Linear evaluation"}. This record does not assert independent reproduction. ### IE-CL Accuracy @ 100 Epochs: 68.3. Result ID: 69b7c54347f34ce9249f8bc1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Batch Size":"256","Evaluation Protocol":"Linear evaluation"}. This record does not assert independent reproduction. ### SimSiam Accuracy @ 100 Epochs: 68.1. Result ID: 69b7c54347f34ce9249f8bbd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Batch Size":"256","Evaluation Protocol":"Linear evaluation"}. This record does not assert independent reproduction. ### MoCo-v2 Accuracy @ 100 Epochs: 67.4. Result ID: 69b7c54347f34ce9249f8bbc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Batch Size":"256","Evaluation Protocol":"Linear evaluation"}. This record does not assert independent reproduction. ### SimCLR Accuracy @ 100 Epochs: 66.5. Result ID: 69b7c54347f34ce9249f8bba. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Batch Size":"4096","Evaluation Protocol":"Linear evaluation"}. This record does not assert independent reproduction. ### SwAV Accuracy @ 100 Epochs: 66.5. Result ID: 69b7c54347f34ce9249f8bbb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Batch Size":"4096","Evaluation Protocol":"Linear evaluation"}. This record does not assert independent reproduction. ### NNCLR Accuracy @ 100 Epochs: 65.4. Result ID: 69b7c54347f34ce9249f8bbe. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Batch Size":"1024","Evaluation Protocol":"Linear evaluation"}. This record does not assert independent reproduction. ### All4One Accuracy @ 100 Epochs: 65.4. Result ID: 69b7c54347f34ce9249f8bbf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Batch Size":"1024","Evaluation Protocol":"Linear evaluation"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.