Multi-label Image Recognition (多标签图像识别) ![](https://camo.githubusercontent.com/38c0ae31aa0389c47d21a3c0cf45597295ed707ebf77b2ce3ac5ff8514bb1a21/68747470733a2f2f76697369746f722d62616467652e676c697463682e6d652f62616467653f706167655f69643d707574616f3533372e417765736f6d652d4d756c74692d6c6162656c2d496d6167652d5265636f676e6974696f6e)
Everything about Multi-label Image Recognition.
Papers •
Tutorials •
Talks •
Blogs •
Datasets & Benchmarks
Multi-label Image Recognition
Pub. |
Title |
Links |
TPAMI |
[P-GCN] Learning Graph Convolutional Networks for Multi-Label Recognition and Applications |
PDF |
TIP |
[MCAR] Learning to Discover Multi-Class Attentional Regions for Multi-Label Image Recognition |
PDF/Code |
TMM |
[DER] Disentangling, Embedding and Ranking Label Cues for Multi-Label Image Recognition |
PDF |
CVPR |
[C-Trans] General Multi-label Image Classification with Transformers |
PDF/Code |
ICCV |
[TDRG] Transformer-based Dual Relation Graph for Multi-label Image Recognition |
PDF/Code |
ICCV |
[ASL] Asymmetric Loss For Multi-Label Classification |
PDF/Code |
ICCV |
[CSRA] Residual Attention: A Simple but Effective Method for Multi-Label Recognition |
PDF/Code |
ICCV |
[TkML-AP] TkML-AP: Adversarial Attacks to Top-k Multi-Label Learning |
PDF |
AAAI |
[DSDL] Deep Semantic Dictionary Learning for Multi-label Image Classification |
PDF/Code |
AAAI |
[MGTN] Modular Graph Transformer Networks for Multi-Label Image Classification |
PDF/Code |
IJCAI |
[GM-MLIC] GM-MLIC: Graph Matching based Multi-Label Image Classification |
PDF |
ACM MM |
[M3TR] M3TR: Multi-modal Multi-label Recognition with Transformer |
PDF/Code |
arxiv |
MlTr: Multi-label Classification with Transformer |
PDF/Code |
arxiv |
Query2Label: A Simple Transformer Way to Multi-Label Classification |
PDF/Code |
arxiv |
Multi-layered Semantic Representation Network for Multi-label Image Classification |
PDF |
arxiv |
Contrast Learning Visual Attention for Multi Label Classification |
PDF |
arxiv |
Learning Discriminative Representations for Multi-Label Image Recognition |
PDF |
Pub. |
Title |
Links |
TPAMI |
[KGGR] Knowledge-Guided Multi-Label Few-Shot Learning for General Image Recognition |
PDF |
TMM |
[DER] Disentangling, Embedding and Ranking Label Cues for Multi-Label Image Recognition |
PDF |
TMM |
[TS-GCN] Joint Input and Output Space Learning for Multi-Label Image Classification |
PDF |
CVPR |
[PLA] Orderless_Recurrent_Models_for_Multi-Label_Classification |
PDF/Code |
ECCV |
[ADD-GCN] Attention-Driven Dynamic Graph Convolutional Network for Multi-Label Image Recognition |
PDF/Code |
AAAI |
[KSSNet] Multi-Label Classification with Label Graph Superimposing |
PDF/Code |
AAAI |
Cross-Modality Attention with Semantic Graph Embedding for Multi-Label Classification |
PDF |
ACM MM |
[SGTN] Privacy-Preserving Visual Content Tagging using Graph Transformer Networks |
PDF/Code |
ACM MM |
[AdaHGNN] AdaHGNN: Adaptive Hypergraph Neural Networks for Multi-Label Image Classification |
PDF |
arxiv |
[IA-GCN] Instance-Aware Graph Convolutional Network for Multi-Label Classification |
PDF |
Pub. |
Title |
Links |
CVPR |
[ML-GCN] Multi-Label Image Recognition with Graph Convolutional Networks |
PDF/Code |
CVPR |
[VAC] Visual Attention Consistency under Image Transforms for Multi-Label Image Classification |
PDF/Code |
ICCV |
[SSGRL] Learning Semantic-Specific Graph Representation for Multi-Label Image Recognition |
PDF/Code |
Pub. |
Title |
Links |
TPAMI'15 |
[HCP] HCP: A Flexible CNN Framework for Multi-Label Image Classification |
PDF |
AAAI'18 |
[Order-Free RNN] Order-Free RNN with Visual Attention for Multi-Label Classification |
PDF |
AAAI'19 |
Recurrent Attentional Reinforcement Learning for Multi-label Image Recognition |
PDF |
IJCAI'18 |
[MsDPD] Multi-scale and Discriminative Part Detectors Based Features for Multi-label Image Classification |
PDF |
ICCV'17 |
[WILDCAT] WILDCAT: Weakly Supervised Learning of Deep ConvNets for Image Classification, Pointwise Localization and Segmentation |
PDF/Code |
ICCV'17 |
[RDAR] Multi-label Image Recognition by Recurrently Discovering Attentional Regions |
PDF/Code |
CVPR'17 |
[SRN] Learning Spatial Regularization with Image-level Supervisions for Multi-label Image Classification |
PDF/Code |
CVPR'16 |
[CNN-RNN] CNN-RNN: A Unified Framework for Multi-label Image Classification |
PDF/Code |
Few/Zero-shot Multi-label Image Recognition
Pub. |
Title |
Links |
TPAMI'20 |
[KGGR] Knowledge-Guided Multi-Label Few-Shot Learning for General Image Recognition |
PDF |
TIP'20 |
Deep Ranking for Image Zero-Shot Multi-Label Classification |
PDF |
ICCV'21 |
[BiAM] Discriminative Region-based Multi-Label Zero-Shot Learning |
PDF/Code |
ICCV'21 |
Semantic Diversity Learning for Zero-Shot Multi-label Classification |
PDF/Code |
ICCV'21 |
Interaction Compass: Multi-Label Zero-Shot Learning of Human-Object Interactions via Spatial Relations |
PDF |
CVPR'20 |
A Shared Multi-Attention Framework for Multi-Label Zero-Shot Learning |
PDF |
CVPR'18 |
Multi-Label Zero-Shot Learning with Structured Knowledge Graphs |
PDF/Code |
CVPR'16 |
Fast Zero-Shot Image Tagging |
PDF/Code |
arxiv |
Multi-Label Learning from Single Positive Labels |
PDF |
Multi-label Image Recognition with Partial Labels
Pub. |
Title |
Links |
TPAMI'21 |
[P-GCN] Learning Graph Convolutional Networks for Multi-Label Recognition and Applications |
PDF |
AAAI'22 |
Semantic-Aware Representation Blending for Multi-Label Image Recognition with Partial Labels |
PDF/Code |
AAAI'22 |
Structured Semantic Transfer for Multi-Label Recognition with Partial Labels |
PDF/Code |
CVPR'21 |
Multi-Label Learning from Single Positive Labels |
PDF |
CVPR'20 |
Interactive Multi-Label CNN Learning with Partial Labels |
PDF |
NeurIPS'20 |
Exploiting weakly supervised visual patterns to learn from partial annotations |
PDF |
CVPR'19 |
Learning a Deep ConvNet for Multi-label Classification with Partial Labels |
PDF |
arxiv |
[ATAM] Rethinking Crowdsourcing Annotation: Partial Annotation with Salient Labels for Multi-Label Image Classification |
PDF |
Multi-label Image Recognition with Nosiy Labels
Pub. |
Title |
Links |
CVPR'19 |
Weakly Supervised Image Classification through Noise Regularization |
PDF |
CVPR'17 |
Learning From Noisy Large-Scale Datasets With Minimal Supervision |
PDF |
Multi-label Image Recognition with Long-tailed Labels
Pub. |
Title |
Links |
CVPR'21 |
Long-Tailed Multi-Label Visual Recognition by Collaborative Training on Uniform and Re-balanced Samplings |
PDF |
ECCV'20 |
Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasets |
PDF/Code |
Tutorials published on 2021
COCO2014
Methods |
Input Size |
Architecture |
mAP |
CP |
CR |
CF1 |
OP |
OR |
OF1 |
ML-GCN (CVPR'19) |
(448, 448) |
CNN-based |
83.0 |
85.1 |
72.0 |
78.0 |
85.8 |
75.4 |
80.3 |
P-GCN(TPAMI'21) |
(448,448) |
CNN-based |
83.2 |
84.9 |
72.7 |
78.3 |
85.0 |
76.4 |
80.5 |
MCAR(TIP'21) |
(448,448) |
CNN-based |
83.8 |
85.0 |
72.1 |
78.0 |
88.0 |
73.9 |
80.3 |
ADD-GCN (ECCV'20) |
(448, 448) |
CNN-based |
85.2 |
84.7 |
75.9 |
80.1 |
84.9 |
79.4 |
82.0 |
SSGRL (ICCV'19) |
(576,576) |
CNN-based |
83.8 |
89.9 |
68.5 |
76.8 |
91.3 |
70.8 |
79.7 |
KGGR (TPAMI'20) |
(576, 576) |
CNN-based |
84.3 |
85.6 |
72.7 |
78.6 |
87.1 |
75.6 |
80.9 |
MCAR(TIP'21) |
(576,576) |
CNN-based |
84.5 |
84.3 |
73.9 |
78.7 |
86.9 |
76.1 |
81.1 |
AdaHGNN(ACM MM'20) |
(576,576) |
CNN-based |
85.0 |
- |
- |
79.9 |
- |
- |
81.8 |
TDRG(ICCV21) |
(448,448) |
CNN-Transformer |
84.6 |
86.0 |
73.1 |
79.0 |
86.6 |
76.4 |
81.2 |
C-Tran(CVPR'21) |
(576,576) |
CNN-Transformer |
85.1 |
86.3 |
74.3 |
79.9 |
87.7 |
76.5 |
81.7 |
TDRG(ICCV'21) |
(576,576) |
CNN-Transformer |
86.0 |
87.0 |
74.7 |
80.4 |
87.5 |
77.9 |
82.4 |
Note: Only present the precision, recall, and F1-measure for all prediction scores.
Visual Genome 500
Methods |
Input Size |
Architecture |
mAP |
CP |
CR |
CF1 |
OP |
OR |
OF1 |
SSGRL (ICCV'19) |
(576,576) |
CNN-based |
36.6 |
- |
- |
- |
- |
- |
- |
KGGR (TPAMI'20) |
(576, 576) |
CNN-based |
37.4 |
48.7 |
12.1 |
19.4 |
78.6 |
17.1 |
28.1 |
AdaHGNN (ACM MM'20) |
(576,576) |
CNN-based |
38.2 |
- |
- |
- |
- |
- |
- |
C-Tran(CVPR'21) |
(576,576) |
CNN-Transformer |
38.4 |
49.8 |
27.2 |
35.2 |
66.9 |
39.2 |
49.5 |
Note: Only present the precision, recall, and F1-measure for all prediction scores.
VOC2007
Methods |
Input Size |
Architecture |
mAP |
CP |
CR |
CF1 |
OP |
OR |
OF1 |
ML-GCN (CVPR'19) |
(448, 448) |
CNN-based |
94.0 |
- |
- |
- |
- |
- |
- |
P-GCN(TPAMI'21) |
(448,448) |
CNN-based |
94.3 |
- |
- |
- |
- |
- |
- |
ADD-GCN (ECCV'20) |
(448,448) |
CNN-based |
96.0 |
- |
- |
- |
- |
- |
- |
SSGRL (ICCV'19) |
(576,576) |
CNN-based |
93.4 |
- |
- |
- |
- |
- |
- |
KGGR (TPAMI'20) |
(576,576) |
CNN-based |
93.6 |
- |
- |
- |
- |
- |
- |
MCAR(TIP'21) |
(576,576) |
CNN-based |
94.8 |
- |
- |
- |
- |
- |
- |
AdaHGNN(ACM MM'20) |
(576,576) |
CNN-based |
95.2 |
- |
- |
- |
- |
- |
- |
TDRG(ICCV21) |
(448,448) |
CNN-Transformer |
95.0 |
- |
- |
- |
- |
- |
- |
Note: Only present the precision, recall, and F1-measure for all prediction scores.