Attention-Driven Dynamic Graph Convolutional Network for Multi-label Image Recognition

Ye, Jin; He, Junjun; Peng, Xiaojiang; Wu, Wenhao; Qiao, Yu

doi:10.1007/978-3-030-58589-1_39

Cited by 122 publications

(87 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We can see that our method achieves the best mAP performance among all methods. We also observe the small margin between our results and ADD-GCN [52]. In addition to the difference in input image resolution (ours 448 × 448 and ADD-GCN's 512 × 512), the small increase may indicate the limited data of VOC 07 and its saturated metric.…”

Section: Performance On Pascal Vocmentioning

confidence: 53%

“…Chen et al [8] constructed a similar graph but based on class-aware maps, which is calculated by image level feature and classification weights, and constrained the graph by label co-occurrence. Rather than using static graph, Ye et al [52] updated static graph to dynamic graph by using a dynamic graph convolutional network(GCN) module for robust representations. While modeling label correlations can introduce additional gains in multi-label classification, it is also arguable that it may learn spurious correlations when the label statistics are insufficient.…”

Section: Multi-label Classificationmentioning

confidence: 99%

See 1 more Smart Citation

Query2Label: A Simple Transformer Way to Multi-Label Classification

Liu,

Zhang,

Yang

et al. 2021

Preprint

View full text Add to dashboard Cite

This paper presents a simple and effective approach to solving the multi-label classification problem. The proposed approach leverages Transformer decoders to query the existence of a class label. The use of Transformer is rooted in the need of extracting local discriminative features adaptively for different labels, which is a strongly desired property due to the existence of multiple objects in one image. The built-in cross-attention module in the Transformer decoder offers an effective way to use label embeddings as queries to probe and pool class-related features from a feature map computed by a vision backbone for subsequent binary classifications. Compared with prior works, the new framework is simple, using standard Transformers and vision backbones, and effective, consistently outperforming all previous works on five multi-label classification data sets, including MS-COCO, PASCAL VOC, NUS-WIDE, and Visual Genome. Particularly, we establish 91.3% mAP on MS-COCO. We hope its compact structure, simple implementation, and superior performance serve as a strong baseline for multi-label classification tasks and future studies. The code will be available soon at https://github.com/SlongLiu/query2labels.

show abstract

Section: Performance On Pascal Vocmentioning

confidence: 53%

Section: Multi-label Classificationmentioning

confidence: 99%

Query2Label: A Simple Transformer Way to Multi-Label Classification

Liu,

Zhang,

Yang

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Hu et al [19] leverages a heterogeneous GNN to handle multiple types of nodes such as topics and entities for text classification. Similarly, we use heterogeneous GNN to obtain the preference scores of each token, but our graph is dynamic as its node correlation matrix is adjustable (inspired by [59]). The final adjusted correlations will be aggregated to obtain preference scores.…”

Section: Graph Neural Network For Text Miningmentioning

confidence: 99%

Integrating Pattern- and Fact-based Fake News Detection via Model Preference Learning

Sheng

Zhang

Cao

et al. 2021

Proceedings of the 30th ACM International Conference on Information &Amp; Knowledge Management

View full text Add to dashboard Cite

To defend against fake news, researchers have developed various methods based on texts. These methods can be grouped as 1) patternbased methods, which focus on shared patterns among fake news posts rather than the claim itself; and 2) fact-based methods, which retrieve from external sources to verify the claim's veracity without considering patterns. The two groups of methods, which have different preferences of textual clues, actually play complementary roles in detecting fake news. However, few works consider their integration. In this paper, we study the problem of integrating patternand fact-based models into one framework via modeling their preference differences, i.e., making the pattern-and fact-based models focus on respective preferred parts in a post and mitigate interference from non-preferred parts as possible. To this end, we build a Preference-aware Fake News Detection Framework (Pref-FEND), which learns the respective preferences of pattern-and fact-based models for joint detection. We first design a heterogeneous dynamic graph convolutional network to generate the respective preference maps, and then use these maps to guide the joint learning of patternand fact-based models for final prediction. Experiments on two realworld datasets show that Pref-FEND effectively captures model preferences and improves the performance of models based on patterns, facts, or both. CCS CONCEPTS• Information systems → Data mining; • Computing methodologies → Natural language processing.

show abstract

“…Zhang et al [42] proposed a hierarchical and transparent representation learning method to express the semantic information for accurate paper-reviewer recommendation as multi-label classification. Ye et al [43] introduced a dynamic graph convolutional network to project raw input into categoryaware representations with semantic attention module, and the final category representations are utilized for multi-label image recognition. Gong et al [44] proposed a hierarchical graph transformer method for multi-label text classification, a multi-layer transformer structure and the hierarchical relationship of the labels are used for feature representations learning in different level.…”

Section: Related Workmentioning

confidence: 99%

Representation Learning With Dual Autoencoder for Multi-Label Classification

Zhu

Yang

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Multi-label classification aims to deal with the problem that an object may be associated with one or more labels, which is a more difficult task due to the complex nature of multi-label data. The crucial problem of multi-label classification is the more robust and higher-level feature representation learning, which can reduce non-helpful feature attributes from the input space prior to training. In recent years, deep learning methods based on autoencoders have achieved excellent performance in multi-label classification for the advantages of powerful representations learning ability and fast convergence speed. However, most existing autoencoder-based methods only rely on the single autoencoder model, which pose challenges for multi-label feature representations learning and fail to measure similarities between data spaces. To address this problem, in this paper, we propose a novel representation learning method with dual autoencoder for multi-label classification. Compared to the existing autoencoder-based methods, our proposed method can capture different characteristics and more abstract features from data by the serially connection of two different types of autoencoders. More specifically, firstly, the algorithm of Reconstruction Independent Component Analysis (RICA) in sparse autoencoder is trained on patches on all training and test dataset for robust global feature representations learning. Secondly, with the output of RICA, stacked autoencoder with manifold regularization (SAMR) is introduced to ameliorate the quality of multi-label features learning. Comprehensive experiments on several real-world data sets demonstrate the effectiveness of our proposed approach compared with several competing state-of-the-art methods.

show abstract

Attention-Driven Dynamic Graph Convolutional Network for Multi-label Image Recognition

Cited by 122 publications

References 35 publications

Query2Label: A Simple Transformer Way to Multi-Label Classification

Query2Label: A Simple Transformer Way to Multi-Label Classification

Integrating Pattern- and Fact-based Fake News Detection via Model Preference Learning

Representation Learning With Dual Autoencoder for Multi-Label Classification

Contact Info

Product

Resources

About