| Open Vocabulary Multi-Label Classification with Dual-Modal Decoder on Aligned Visual-Textual Features | | 93.54 | ADDS(ViT-L-336, resolution 1344) | 2022-08-19 |
| Open Vocabulary Multi-Label Classification with Dual-Modal Decoder on Aligned Visual-Textual Features | | 93.41 | ADDS(ViT-L-336, resolution 640) | 2022-08-19 |
| Open Vocabulary Multi-Label Classification with Dual-Modal Decoder on Aligned Visual-Textual Features | | 91.76 | ADDS(ViT-L-336, resolution 336) | 2022-08-19 |
| ML-Decoder: Scalable and Versatile Classification Head | ✓ Link | 91.4 | ML-Decoder(TResNet-XL, resolution 640) | 2021-11-25 |
| Query2Label: A Simple Transformer Way to Multi-Label Classification | ✓ Link | 91.3 | Q2L-CvT(ImageNet-21K pretraining, resolution 384) | 2021-07-22 |
| Combining Metric Learning and Attention Heads For Accurate and Efficient Multilabel Image Classification | ✓ Link | 91.30 | MLD-TResNet-L-AAM[640x640] | 2022-09-14 |
| ML-Decoder: Scalable and Versatile Classification Head | ✓ Link | 91.1 | ML-Decoder(TResNet-L, resolution 640) | 2021-11-25 |
| Query2Label: A Simple Transformer Way to Multi-Label Classification | ✓ Link | 90.5 | Q2L-SwinL(ImageNet-21K pretraining, resolution 384) | 2021-07-22 |
| Query2Label: A Simple Transformer Way to Multi-Label Classification | ✓ Link | 90.3 | Q2L-TResL(ImageNet-21K pretraining, resolution 640) | 2021-07-22 |
| Causality Compensated Attention for Contextual Biased Visual Recognition | ✓ Link | 90.3 | IDA-SwinL | 2023-02-25 |
| Contextual Debiasing for Visual Recognition With Causal Mechanisms | ✓ Link | 90.3 | CCD-SwinL | 2022-01-01 |
| MlTr: Multi-label Classification with Transformer | ✓ Link | 90.0 | MlTr-XL(ImageNet-21K pretraining, resolution 384) | 2021-06-11 |
| ImageNet-21K Pretraining for the Masses | ✓ Link | 89.8 | TResNet-L-V2, (ImageNet-21K-P pretraining, resolution 640) | 2021-04-22 |
| MlTr: Multi-label Classification with Transformer | ✓ Link | 88.5 | MlTr-L(ImageNet-21K pretraining, resolution 384) | 2021-06-11 |
| Asymmetric Loss For Multi-Label Classification | ✓ Link | 88.4 | TResNet-XL (resolution 640) | 2020-09-29 |
| ImageNet-21K Pretraining for the Masses | ✓ Link | 88.4 | TResNet-L-V2, (ImageNet-21K-P pretraining, resolution 448) | 2021-04-22 |
| GKGNet: Group K-Nearest Neighbor based Graph Convolutional Network for Multi-Label Image Recognition | ✓ Link | 87.7 | GKGNet(resolution 576) | 2023-08-28 |
| M3TR: Multi-modal Multi-label Recognition with Transformer | ✓ Link | 87.5 | M3TR(ImageNet-21K-P pretraining, resolution 448) | 2021-10-01 |
| GKGNet: Group K-Nearest Neighbor based Graph Convolutional Network for Multi-Label Image Recognition | ✓ Link | 86.7 | GKGNet(resolution 448) | 2023-08-28 |
| Asymmetric Loss For Multi-Label Classification | ✓ Link | 86.6 | TResNet-L (resolution 448) | 2020-09-29 |
| Causality Compensated Attention for Contextual Biased Visual Recognition | ✓ Link | 86.3 | IDA-R101 | 2023-02-25 |
| Transformer-based Dual Relation Graph for Multi-label Image Recognition | ✓ Link | 86.0 | TDRG-R101(576×576) | 2021-10-10 |
| Contextual Debiasing for Visual Recognition With Causal Mechanisms | ✓ Link | 85.3 | CCD-R101 | 2022-01-01 |
| Attention-Driven Dynamic Graph Convolutional Network for Multi-Label Image Recognition | ✓ Link | 85.2 | ADD-GCN | 2020-12-05 |
| Query2Label: A Simple Transformer Way to Multi-Label Classification | ✓ Link | 84.9 | Q2L-R101(resolution 448) | 2021-07-22 |
| Transformer-based Dual Relation Graph for Multi-label Image Recognition | ✓ Link | 84.6 | TDRG-R101(448×448) | 2021-10-10 |
| Learning to Discover Multi-Class Attentional Regions for Multi-Label Image Recognition | ✓ Link | 84.5 | MCAR (ResNet101, 576x576) | 2020-07-03 |
| Cross-Modality Attention with Semantic Graph Embedding for Multi-Label Classification | | 83.8 | MS-CMA | 2019-12-17 |
| Learning to Discover Multi-Class Attentional Regions for Multi-Label Image Recognition | ✓ Link | 83.8 | MCAR (ResNet101, 448x448) | 2020-07-03 |
| Multi-Label Classification with Label Graph Superimposing | ✓ Link | 83.7 | KSSNet | 2019-11-21 |
| Multi-layered Semantic Representation Network for Multi-label Image Classification | ✓ Link | 83.4 | MSRN | 2021-06-22 |
| Multi-Label Graph Convolutional Network Representation Learning | | 83.0 | ML-GCN | 2019-12-26 |
| GKGNet: Group K-Nearest Neighbor based Graph Convolutional Network for Multi-Label Image Recognition | ✓ Link | 82 | GKGNet(resolution 224) | 2023-08-28 |
| Learning Spatial Regularization with Image-level Supervisions for Multi-label Image Classification | ✓ Link | 77.1 | ResNet-SRN | 2017-02-20 |