# Multi-label Classification on ImageNet Seg Source: [Multi-label Classification on ImageNet Seg]() Collection index: [llms.txt]() Data updated: 2026-03-09T07:29:29.719Z Evaluation of Multi-label Classification performance on the ImageNet Seg dataset, reporting metrics such as Top-1 Accuracy and mAP. 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 | Multi-label Classification | | Dataset (including any stated split) | ImageNet Seg | | Metric | Top-1 Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 18 of 18 | | 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. - [mAP](): Higher is better; unit: PERCENT. ## Recorded results | Method | Top-1 Accuracy | Result date | Report paper | | --- | --- | --- | --- | | +Multi-label FT | 89.4 | Not recorded | 69ae53fa2d603e6de3e42aa8 | | Multi-label E2E | 89.4 | Not recorded | 69ae53fa2d603e6de3e42aa8 | | +IN1k-Mul FT | 89.2 | Not recorded | 69ae53fa2d603e6de3e42aa8 | | Multi-label E2E | 89.1 | Not recorded | 69ae53fa2d603e6de3e42aa8 | | IN1k-Mul E2E | 89.1 | Not recorded | 69ae53fa2d603e6de3e42aa8 | | +Multi-label FT | 88.8 | Not recorded | 69ae53fa2d603e6de3e42aa8 | | +IN1k-Sig FT | 88.8 | Not recorded | 69ae53fa2d603e6de3e42aa8 | | Single-label E2E | 88.5 | Not recorded | 69ae53fa2d603e6de3e42aa8 | | Multi-label E2E | 88.3 | Not recorded | 69ae53fa2d603e6de3e42aa8 | | Single-label E2E | 88.2 | Not recorded | 69ae53fa2d603e6de3e42aa8 | | +Multi-label FT | 87.8 | Not recorded | 69ae53fa2d603e6de3e42aa8 | | Single-label E2E | 87.2 | Not recorded | 69ae53fa2d603e6de3e42aa8 | | +Multi-label FT | 87.1 | Not recorded | 69ae53fa2d603e6de3e42aa8 | | Multi-label E2E | 86.9 | Not recorded | 69ae53fa2d603e6de3e42aa8 | | +Multi-label FT | 85.9 | Not recorded | 69ae53fa2d603e6de3e42aa8 | | Multi-label E2E | 85.5 | Not recorded | 69ae53fa2d603e6de3e42aa8 | | Single-label E2E | 85.3 | Not recorded | 69ae53fa2d603e6de3e42aa8 | | Single-label E2E | 84.4 | Not recorded | 69ae53fa2d603e6de3e42aa8 | ### +Multi-label FT Top-1 Accuracy: 89.4. Result ID: 69ae765f6dbb7075b95632cb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ViT-large"}. This record does not assert independent reproduction. ### Multi-label E2E Top-1 Accuracy: 89.4. Result ID: 69ae765f6dbb7075b95632cc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ViT-large"}. This record does not assert independent reproduction. ### +IN1k-Mul FT Top-1 Accuracy: 89.2. Result ID: 69ae765f6dbb7075b956330d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT-B/16","Resolution":"224","Pre-training":"ImageNet-21K (MIIL)","Supervision":"Multi-label (Mul)","Training Protocol":"Fine-tuning"}. This record does not assert independent reproduction. ### Multi-label E2E Top-1 Accuracy: 89.1. Result ID: 69ae765f6dbb7075b95632c9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ViT-base"}. This record does not assert independent reproduction. ### IN1k-Mul E2E Top-1 Accuracy: 89.1. Result ID: 69ae765f6dbb7075b956330e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT-B/16","Resolution":"224","Supervision":"Multi-label (Mul)","Training Protocol":"End-to-end"}. This record does not assert independent reproduction. ### +Multi-label FT Top-1 Accuracy: 88.8. Result ID: 69ae765f6dbb7075b95632c8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ViT-base"}. This record does not assert independent reproduction. ### +IN1k-Sig FT Top-1 Accuracy: 88.8. Result ID: 69ae765f6dbb7075b956330c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ViT-B/16","Resolution":"224","Pre-training":"ImageNet-21K (MIIL)","Supervision":"Single-label (Sig)","Training Protocol":"Fine-tuning"}. This record does not assert independent reproduction. ### Single-label E2E Top-1 Accuracy: 88.5. Result ID: 69ae765f6dbb7075b95632ca. [Reporting paper]() Recorded evaluation configuration: {"Model":"ViT-large"}. This record does not assert independent reproduction. ### Multi-label E2E Top-1 Accuracy: 88.3. Result ID: 69ae765f6dbb7075b95632c6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ViT-small"}. This record does not assert independent reproduction. ### Single-label E2E Top-1 Accuracy: 88.2. Result ID: 69ae765f6dbb7075b95632c7. [Reporting paper]() Recorded evaluation configuration: {"Model":"ViT-base"}. This record does not assert independent reproduction. ### +Multi-label FT Top-1 Accuracy: 87.8. Result ID: 69ae765f6dbb7075b95632c5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ViT-small"}. This record does not assert independent reproduction. ### Single-label E2E Top-1 Accuracy: 87.2. Result ID: 69ae765f6dbb7075b95632c4. [Reporting paper]() Recorded evaluation configuration: {"Model":"ViT-small"}. This record does not assert independent reproduction. ### +Multi-label FT Top-1 Accuracy: 87.1. Result ID: 69ae765f6dbb7075b95632c2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ResNet-101"}. This record does not assert independent reproduction. ### Multi-label E2E Top-1 Accuracy: 86.9. Result ID: 69ae765f6dbb7075b95632c3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ResNet-101"}. This record does not assert independent reproduction. ### +Multi-label FT Top-1 Accuracy: 85.9. Result ID: 69ae765f6dbb7075b95632bf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ResNet-50"}. This record does not assert independent reproduction. ### Multi-label E2E Top-1 Accuracy: 85.5. Result ID: 69ae765f6dbb7075b95632c0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ResNet-50"}. This record does not assert independent reproduction. ### Single-label E2E Top-1 Accuracy: 85.3. Result ID: 69ae765f6dbb7075b95632c1. [Reporting paper]() Recorded evaluation configuration: {"Model":"ResNet-101"}. This record does not assert independent reproduction. ### Single-label E2E Top-1 Accuracy: 84.4. Result ID: 69ae765f6dbb7075b95632be. [Reporting paper]() Recorded evaluation configuration: {"Model":"ResNet-50"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.