# Image Retrieval on ImageNet-100 (val) Source: [Image Retrieval on ImageNet-100 (val)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:07:02.218Z Evaluation of Image Retrieval performance on the validation split of the ImageNet-100 dataset, measured using Top-1 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 Retrieval | | Dataset (including any stated split) | ImageNet 100 (val) | | Metric | Top-1 Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 10 of 10 | | 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 - [Top-1 Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Top-1 Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Places | 57.04 | Not recorded | 68fa71b91e209131cea52c9a | | LLMs (w/o GPT-4) + S-21k | 43.4 | Not recorded | 68fa71b91e209131cea52c9a | | LLMs (w/ GPT-4) + S-21k | 43.36 | Not recorded | 68fa71b91e209131cea52c9a | | S-21k | 43.24 | Not recorded | 68fa71b91e209131cea52c9a | | StyleGAN O | 33 | Not recorded | 68fa71b91e209131cea52c9a | | LLMs (w/ GPT-4) | 27.44 | Not recorded | 68fa71b91e209131cea52c9a | | LLMs (w/o GPT-4) | 22.42 | Not recorded | 68fa71b91e209131cea52c9a | | FractalDB-1k | 17.24 | Not recorded | 68fa71b91e209131cea52c9a | | Dead-leaves | 12.76 | Not recorded | 68fa71b91e209131cea52c9a | | Random Initialization | 4.28 | Not recorded | 68fa71b91e209131cea52c9a | ### Places Top-1 Accuracy: 57.04. Result ID: 6991dd523a6c3148490b1511. [Reporting paper]() Recorded evaluation configuration: {"Pre-training Dataset":"Places","Evaluation Protocol":"5-NN retrieval","Backbone":"ResNet-50","Algorithm":"MoCo-v2"}. This record does not assert independent reproduction. ### LLMs (w/o GPT-4) + S-21k Top-1 Accuracy: 43.4. Result ID: 6991dd523a6c3148490b1518. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pre-training Dataset":"LLM (w/o GPT-4) combined with Shaders-21k","Evaluation Protocol":"5-NN retrieval","Backbone":"ResNet-50","Algorithm":"MoCo-v2"}. This record does not assert independent reproduction. ### LLMs (w/ GPT-4) + S-21k Top-1 Accuracy: 43.36. Result ID: 6991dd523a6c3148490b1519. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pre-training Dataset":"LLM (w/ GPT-4) combined with Shaders-21k","Evaluation Protocol":"5-NN retrieval","Backbone":"ResNet-50","Algorithm":"MoCo-v2"}. This record does not assert independent reproduction. ### S-21k Top-1 Accuracy: 43.24. Result ID: 6991dd523a6c3148490b1515. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-training Dataset":"S-21k","Evaluation Protocol":"5-NN retrieval","Backbone":"ResNet-50","Algorithm":"MoCo-v2"}. This record does not assert independent reproduction. ### StyleGAN O Top-1 Accuracy: 33. Result ID: 6991dd523a6c3148490b1514. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-training Dataset":"StyleGAN O","Evaluation Protocol":"5-NN retrieval","Backbone":"ResNet-50","Algorithm":"MoCo-v2"}. This record does not assert independent reproduction. ### LLMs (w/ GPT-4) Top-1 Accuracy: 27.44. Result ID: 6991dd523a6c3148490b1517. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pre-training Dataset":"LLM-generated images (including GPT-4)","Evaluation Protocol":"5-NN retrieval","Backbone":"ResNet-50","Algorithm":"MoCo-v2"}. This record does not assert independent reproduction. ### LLMs (w/o GPT-4) Top-1 Accuracy: 22.42. Result ID: 6991dd523a6c3148490b1516. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pre-training Dataset":"LLM-generated images (excluding GPT-4)","Evaluation Protocol":"5-NN retrieval","Backbone":"ResNet-50","Algorithm":"MoCo-v2"}. This record does not assert independent reproduction. ### FractalDB-1k Top-1 Accuracy: 17.24. Result ID: 6991dd523a6c3148490b1513. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-training Dataset":"FractalDB-1k","Evaluation Protocol":"5-NN retrieval","Backbone":"ResNet-50","Algorithm":"MoCo-v2"}. This record does not assert independent reproduction. ### Dead-leaves Top-1 Accuracy: 12.76. Result ID: 6991dd523a6c3148490b1512. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-training Dataset":"Dead-leaves","Evaluation Protocol":"5-NN retrieval","Backbone":"ResNet-50","Algorithm":"MoCo-v2"}. This record does not assert independent reproduction. ### Random Initialization Top-1 Accuracy: 4.28. Result ID: 6991dd523a6c3148490b1510. [Reporting paper]() Recorded evaluation configuration: {"Pre-training Dataset":"None","Evaluation Protocol":"5-NN retrieval","Backbone":"ResNet-50","Algorithm":"MoCo-v2"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.