Awesome-Multi-label-image-classification

We've compiled a list of related work in this not-so-popular multi-label field. We hope it will be helpful to the researchers involved.

1. Benchmark Datasets (Average labels per image(ALP))

Dataset	# Class	# Training data	# Test data	#ALP
Pascal VOC 2007 (VOC07)	20	5,011	4952	2.5
Pascal VOC 2012 (VOC12)	20	11,540	10,991	2.5
MS-COCO 2014 (COCO)	80	82,081	40,504	2.9
MS-COCO 2017 (COCO17)	80	118,287	40,670	-
NUS-WIDE (NW)	81	125,449	83898	2.4
WIDER Attribute (WA)	14	28,345	29,179	-
PA-100K (PA)	26	9,000	1,000	-
Fashion550K (F550)	66	3300	2000	-
Charades (Cha)	157	8,000	1,800	6.8
Visual Genome (VG500)	500	75,774	32,475	-
Visual Genome (VG256)	256	75,774	32,475	-
IAPRTC-12 (IA12)	275	13,989	6,011	-
DeepFashion (DF)	26	16,000	4,000	-
CUB-200-2011 (CUB)	200	5,994	5,794	-

2. Top-tier Conference Papers

2014--2019

Title	Venue	Year	Datasets	Code
[WARP]Deep Convolutional Ranking for Multilabel Image Annotation	ICLR	2014	NW	-
[HCP]HCP: AFlexible CNN Framework for Multi-Label Image Classification	TPAMI	2016	VOC07,VOC12	-
[CNN-RNN]CNN-RNN: AUnified Framework for Multi-label Image Classification	CVPR	2016	NW,COCO,VOC07	Official
[FeV+LV]Exploit Bounding Box Annotations for Multi-Label Object Recognition	CVPR	2016	VOC07,VOC12	-
[RCP]Beyond Object Proposals: Random Crop Pooling for Multi-Label Image Recognition	TIP	2016	VOC07,VOC12	-
[SRN]Learning Spatial Regularization with Image-level Supervisions for Multi-label Image Classification	CVPR	2017	NW,COCO	Official
[LSEP]Improving Pairwise Ranking for Multi-label Image Classification	CVPR	2017	NW,COCO,VOC07	Official
[Order-Free RNN]Order-Free RNN with Visual Attention for Multi-Label Classification	AAAI	2017	NW,COCO	-
[Multi-Evidence]Multi-Evidence Filtering and Fusion for Multi-Label Classification, Object Detection and Semantic Segmentation Based on Weakly Supervised Learning	CVPR	2017	COCO,VOC07,VOC12	-
[RDAR]Multi-label Image Recognition by Recurrently Discovering Attentional Regions	ICCV	2017	COCO,VOC07	Official
[KD-WSD]Multi-Label Image Classification via Knowledge Distillation from Weakly-Supervised Detection	ACM MM	2018	NW,COCO	Official
[RLSD]Multilabel Image Classification With Regional Latent Semantic Dependencies	TMM	2018	NW,COCO,VOC07	-
[RARL]Recurrent Attentional Reinforcement Learning for Multi-label Image Recognition	AAAI	2018	COCO,VOC07	-
[RMIC]Reinforced Multi-label Image Classification by Exploring Curriculum	AAAI	2018	VOC07,VOC12	-
[MsDPD]Multi-scale and Discriminative Part Detectors Based Features for Multi-label Image Classification	IJCAI	2018	VOC07,VOC12	-
[ML-GCN]Multi-label Image Recognition With Graph Convolutional Networks	CVPR	2019	COCO,VOC07	Official
[SSGRL]Learning Semantic-specific Graph Representation for Multi-label Image Recognition	ICCV	2019	COCO,VOC07,VOC12	Official
[CADM]Multi-label Image Recognition with Joint Class-aware Map Disentangling and Label Correlation Embedding	ICME	2019	NW,COCO	-
[ACfs]Visual Attention Consistency under Image Transforms for Multi-Label Image Classification	CVPR	2019	COCO,WA,PA	Official
[CoP]Multilabel Image Classification via Feature/Label Co-Projection	TSMC	2019	COCO,VOC07	-
[DELTA]DELTA: A deep dual-stream network for multi-label image classification	PR	2019	COCO,VOC07	-

2020

Title	Venue	Year	Datasets	Code
[PLA]Orderless Recurrent Models for Multi-label Classification	CVPR	2020	NW,COCO,WA,PA	Official
[TSGCN]Joint Input and Output Space Learning for Multi-Label Image Classification	TMM	2020	COCO,VOC07	-
[CMA]Cross-Modality Attention with Semantic Graph Embedding for Multi-Label Classification	AAAI	2020	NW,COCO	-
[KSSNet]Multi-Label Classification with Label Graph Superimposing	AAAI	2020	COCO,Cha	Official
[A-GCN]Learning Class Correlations for Multi-label Image Recognition with Graph Networks	PRL	2020	COCO,F550	Official
[ADD-GCN]Attention-Driven Dynamic Graph Convolutional Network for Multi-label Image Recognition	ECCV	2020	COCO,VOC07,VOC12	Official
[F-GCN]Fast Graph Convolution Network Based Multi-label Image Recognition via Cross-modal Fusion	CIKM	2020	COCO,VOC07	-
[MSSAF]Multi-scale Cross-modal Spatial Attention Fusion for Multi-label Image Recognition	ICANN	2020		-

2021

Title	Venue	Year	Datasets	Code
[MCAR]Learning to Discover Multi-Class Attentional Regions for Multi Label Image Recognition	TIP	2021	COCO,VOC07,VOC12	Official
[GM-MLIC]GM-MLIC: Graph Matching based Multi-Label Image Classification	IJCAI	2021	NW,COCO,VOC07	-
[MGTN]Modular Graph Transformer Networks for Multi-Label Image Classification	AAAI	2021	COCO,F550	Official
[DSDL]Deep Semantic Dictionary Learning for Multi-label Image Classification	AAAI	2021	COCO,VOC07,VOC12	Official
[Q2L]Query2Label: A Simple Transformer Way to Multi-Label Classification	arXiv	2021	NW,COCO,VOC07,VOC12,VG500	Official
[C-Tran]General Multi-label Image Classification with Transformers	CVPR	2021	COCO,VG500	Official
[CSRA]Residual Attention: A Simple But Effective Method for Multi-Label Recoginition	ICCV	2021	COCO,VOC07,VOC12,WA	Official
[ASL]Asymmetric Loss For Multi-Label Classification/supp	ICCV	2021	NW,COCO,VOC07	Official
[TDRG]Transformer-based Dual Relation Graph for Multi-label Image Recognition	ICCV	2021	COCO,VOC07	Official
[TkML-AP]TkML-AP: Adversarial Attacks to Top-k Multi-Label Learning	ICCV	2021	COCO,VOC12	Official
[M3TR]M3TR: Multi-modal Multi-label Recog nition with Transformer	ACM MM	2021	COCO,VOC07	Official
[AdaHGNN]AdaHGNN: Adaptive Hypergraph Neural Networks for Multi-Label Image Classification	ACM MM	2021	NW,COCO,VOC07,VG500	-
[Deep-LIFT]Deep-LIFT: Deep Label-Specific Feature Learning for Image Annotation	TCYB	2021	COCO,VOC07	Official
[DRTE]Distance Restricted Transformer Encoder for Multi-Label Classification	ICME	2021	COCO,WA	Official

2022

Title	Venue	Year	Datasets	Code
[CPSD]Boosting Multi-Label Image Classification with Complementary Parallel Self-Distillation	IJCAI	2022	NW,COCO	Official
[Global Meets Local]Global Meets Local: Effective Multi-Label Image Classification via Category-Aware Weak Supervision	ACM MM	2022	COCO,VOC07	-
[TSFormer]Two-Stream Transformer for Multi-Label Image Classification	ACM MM	2022	NW,COCO,VOC07	Official
[LGR]Label-aware Graph Representation Learning for Multi-label Image Classification	Neurocomputing	2022	COCO,VOC07,VOC12	-
[GCN-MS-SGA]A Multi-scale Semantic Attention Representation for Multi-label Image Recognition with Graph Networks	Neurocomputing	2022	COCO,VOC07	-
[HGT&BC]Hierarchical GAN-Tree and Bi-Directional Capsules for Multi-label Image Classification	KBS	2022	NW,COCO,VOC07,IA12	-
[SSNP]Semantic Supplementary Network With Prior Information for Multi-Label Image Classification	TCSVT	2022	NW,COCO,VOC07	-
[CPCL]Multi-Label Image Classification via Category Prototype Compositional Learning	TCSVT	2022	NW,COCO,VOC07	Official
[SST]SST: Spatial and Semantic Transformers for Multi-Label Image Recognition	TIP	2022	NW,COCO,VOC07	-
[KGGR]Knowledge-Guided Multi-Label Few-Shot Learning for General Image Recognition	TPAMI	2022	COCO,VOC07,VOC12,VG500	-
[MLTR]MLTR: Multi-Label Classification with Transformer	ICME	2022	NW,COCO,VOC07	-
[DualCoOp]DualCoOp: Fast Adaptation to Multi-Label Recognition with Limited Annotations	NeurIPS	2022	NW,COCO,VOC07	Official
[C-GMVAE]Gaussian Mixture Variational Autoencoder with Contrastive Learning for Multi-Label Classification	ICML	2022	-	Official

2023

Title	Venue	Year	Datasets	Code
[MuMIC]MuMIC-Multimodal Embedding for Multi-Label Image Classification with Tempered Sigmoid	AAAI	2023	-	-
[MKT]Open-Vocabulary Multi-Label Classification via Multi-Modal Knowledge Transfer	AAAI	2023	NW,open	Official
[CDUL]CDUL: CLIP-Driven Unsupervised Learning for Multi-Label Image Classification	ICCV	2023	NW,COCO,VOC07,VOC12	Official
[PatchCT]PatchCT: Aligning Patch Set and Label Set with Conditional Transport for Multi-Label Image Classification	ICCV	2023	NW,COCO,VOC07	-
[SALGL]Scene-Aware Label Graph Learning for Multi-Label Image Classification	ICCV	2023	NW,COCO,VOC07	Official
[HSVLT]HSVLT: Hierarchical Scale-Aware Vision-Language Transformer for Multi-Label Image Classification	ACM MM	2023	NW,COCO,VOC07	Official
[SCO-DCNN]Spatial Context-Aware Object-Attentional Network for Multi-Label Image Classification	TIP	2023	COCO17,VOC07	-
[VSGCN]Beyond Word Embeddings: Heterogeneous Prior Knowledge Driven Multi-Label Image Classification	TMM	2023	NW,COCO,VOC07	-
[P-GCN]Learning Graph Convolutional Networks for Multi-Label Recognition and Applications	TPAMI	2023	NW,COCO,VOC07	-
[MulCon]Contrastively enforcing distinctiveness for multi-label image classification	Neurocomputing	2023	NW,COCO,VOC07,VG500	Official
[BM]Balanced Masking Strategy for Multi-label Image Classification	Neurocomputing	2023	COCO,VOC07	-
[FL-Tran]Feature Learning Network with Transformer for Multi-label Image Classification	PR	2023	NW,COCO,VOC07	-
[ML-Decoder]ML-Decoder: Scalable and Versatile Classification Head	WACV	2023	NW,COCO,VOC07	Official
[DDA-MLIC]Discriminator-free Unsupervised Domain Adaptation for Multi-label Image Classification	WACV	2023	-	Official
[AAMN]Attention-Augmented Memory Network for Image Multi-Label Classification	ACM TMCCA	2023	COCO,VOC07,VG500	-
[DualCoOp++]DualCoOp++: Fast and Effective Adaptation to Multi-Label Recognition with Limited Annotations	TPAMI	2023	NW,COCO,VOC07	Official
[SADCL]Semantic-Aware Dual Contrastive Learning for Multi-label Image Classification	ECAI	2023	NW,COCO,VOC07,VOC12,VG500	Official

2024

Title	Venue	Year	Datasets	Code
[HSQ]Hybrid Sharing for Multi-Label Image Classification	ICLR	2024	COCO,VOC07	Official
[MLC-PAT]Counterfactual Reasoning for Multi-Label Image Classification via Patching-Based Training	ICML	2024	COCO,VOC07,VG256	Official
[DRGN]Mining Semantic Information With Dual Relation Graph Network for Multi-Label Image Classification	TMM	2024	COCO,VOC07,VG500	-
[CCR]Conditional Consistency Regularization for Semi-Supervised Multi-Label Image Classification	TMM	2024	COCO,VOC07	-
[DATran]DATran: Dual Attention Transformer for Multi-Label Image Classification	TCSVT	2024	COCO,VOC07,VG500	-
[C-TMS]Transformer Driven Matching Selection Mechanism for Multi-Label Image Classification	TCSVT	2024	NW,COCO,VOC07,VOC12	-
[BalanceMix]Toward Robustness in Multi-Label Classification: A Data Augmentation Strategy against Imbalance and Noise	AAAI	2024	COCO,VOC07,DF	Official
[TKPR]Top-K Pairwise Ranking: Bridging the Gap Among Ranking-Based Measures for Multi-label Classification	IJCV	2024	NW,COCO,VOC07	-
				Official

2025

Title	Venue	Year	Datasets	Code
[FFTran]Transformer-driven Feature Fusion Network and Visual Feature Coding for Multi-label Image Classification	PR	2025	NW,COCO,VOC07,VOC12	-
[SpliceMix]SpliceMix: A Cross-scale and Semantic Blending Augmentation Strategy for Multi-label Image Classification	TMM	2025	COCO,VOC07	Official
[TsSAN]Two-stream Semantic Alignment Networks for Multi-label Image Classification	ICASSP	2025	NW,COCO,VOC07	-
[-]Multi-Label Few-Shot Image Classification via Pairwise Feature Augmentation and Flexible Prompt Learning	AAAI	2025	COCO,VOC12	-
[HP-DVAL]Dual-View Alignment Learning With Hierarchical-Prompt for Class-Imbalance Multi-Label Image Classification	TIP	2025	COCO,VOC07	Official
[DRTN]DRTN: Dual Relation Transformer Network with feature erasure and contrastive learning for multi-label image classification	NN	2025	NW,COCO,VOC07	-
				Official

3. Other Resources

• Awesome-Multi-label-Image-Recognition
• Multi-label Image Recognition