Query2Label: A Simple Transformer Way to Multi-Label Classification | ✓ Link | 97.3 | Q2L-CvT(ImageNet-21K pretrained, resolution 384) | 2021-07-22 |
Query2Label: A Simple Transformer Way to Multi-Label Classification | ✓ Link | 96.9 | Q2L-TResL(ImageNet-21K pretrained, resolution 448) | 2021-07-22 |
GKGNet: Group K-Nearest Neighbor based Graph Convolutional Network for Multi-Label Image Recognition | ✓ Link | 96.8 | GKGNet | 2023-08-28 |
Combining Metric Learning and Attention Heads For Accurate and Efficient Multilabel Image Classification | ✓ Link | 96.70 | MLD-TResNetL-AAM (resolution 448, pretrain from OpenImages V6) | 2022-09-14 |
M3TR: Multi-modal Multi-label Recognition with Transformer | ✓ Link | 96.5 | M3TR(448×448) | 2021-10-01 |
Query2Label: A Simple Transformer Way to Multi-Label Classification | ✓ Link | 96.1 | Q2L-TResL(resolution 448) | 2021-07-22 |
Multi-layered Semantic Representation Network for Multi-label Image Classification | ✓ Link | 96.0 | MSRN(pretrain from MS-COCO) | 2021-06-22 |
Asymmetric Loss For Multi-Label Classification | ✓ Link | 95.8 | TResNet-L (resolution 448, pretrain from MS-COCO) | 2020-09-29 |
Learning Semantic-Specific Graph Representation for Multi-Label Image Recognition | ✓ Link | 95.0 | SSGRL (pretrain from MS-COCO) | 2019-08-20 |
Transformer-based Dual Relation Graph for Multi-label Image Recognition | ✓ Link | 95.0 | TDRG-R101(448×448) | 2021-10-10 |
Learning to Discover Multi-Class Attentional Regions for Multi-Label Image Recognition | ✓ Link | 94.8 | MCAR (ResNet101, 448x448) | 2020-07-03 |
Asymmetric Loss For Multi-Label Classification | ✓ Link | 94.6 | TResNet-L (resolution 448, pretrain from ImageNet) | 2020-09-29 |
Multi-Label Image Recognition with Graph Convolutional Networks | ✓ Link | 94.0 | ML-GCN (pretrain from ImageNet) | 2019-04-07 |
Learning Semantic-Specific Graph Representation for Multi-Label Image Recognition | ✓ Link | 93.4 | SSGRL (pretrain from ImageNet) | 2019-08-20 |
Deep Label Distribution Learning with Label Ambiguity | ✓ Link | 93.4 | Ours PF-DLDL | 2016-11-06 |
ImageNet-21K Pretraining for the Masses | ✓ Link | 93.1 | ViT-B-16 (ImageNet-21K pretrained) | 2021-04-22 |
Exploit Bounding Box Annotations for Multi-label Object Recognition | | 92.0 | FeV+LV (pretrain from ImageNet) | 2015-04-22 |