Edge-Labeling Graph Neural Network for Few-Shot Learning

Kim, Jongmin; Kim, Taesup; Kim, Sungwoong; Yoo, Chang D.

doi:10.1109/cvpr.2019.00010

Cited by 408 publications

(285 citation statements)

References 13 publications

Supporting

Mentioning

282

Contrasting

Unclassified

Order By: Relevance

“…Moreover, PRN designs a novel loss function, which takes both inter-class and intra-class distance into account. References [26] and [27] use the graph convolutional network (GNN) to solve the few-shot recognition problem. According to the similarity between nodes, GNN selectively spreads the image information of the existing label to the test image that is most similar to it.…”

Section: B Metric Learning-based Methodsmentioning

confidence: 99%

Multi-Scale Decision Network with Feature Fusion and Weighting for Few-Shot Learning

Wang

Yu³

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Learning from limited labelled examples is key a research hotspot with excellent scenarios and potential applications. Currently, most of metric learning-based few-shot models still have the problem of low recognition accuracy. This is mainly because that they only use the top-layer abstract feature with semantic information, which ignores the low-layer features that are also critical for the few-shot recognition. Therefore, the extracted features do not have abundant representation ability, and it is difficult to recognize easily confusing objects. Moreover, they usually adopt a fixed distance function or train a comparable network to measure features. These methods lack adaptability, cannot sufficiently fuse features, which leads to weaken the fitting ability of the metric function. And the same or different classes of images are treated equally, which makes the metric function have no emphasis point during training. To address these issues, we propose an end-to-end, metric learning-based model in this paper, called multi-scale decision network with feature fusion and weighting for few-shot learning (MSDN). Considering the importance of the low-layer features, we exploit a convolutional network to extract each layer feature. Then, we exploit a relation network to learn a non-linear metric between the support set and the query set features of each layer and classify the test images via a voting decision. During feature concatenation, we design a non-linear feature fusion item to improve the way of concatenation, so that the relation network can have a stronger function fitting ability to learn the relation score. Meanwhile, we introduce the attention mechanism by calculating the cosine similarity between the support set and the query set features as their weight, which makes the relation network pay more attention to the same class of images. Our model achieves the state-ofthe-art accuracy result on Omniglot and miniImageNet datasets compared with popular few-shot recognition models. INDEX TERMS Feature fusion, feature weighting, few-shot learning, image recognition, multi-scale feature.

show abstract

Section: B Metric Learning-based Methodsmentioning

confidence: 99%

Multi-Scale Decision Network with Feature Fusion and Weighting for Few-Shot Learning

Wang

Yu³

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…With the strong abstracting power of the deep neural network [8,13,15,16,22], some deep HDA methods are developed to further the performance boundary of HDA tasks. Weakly-shared Deep Transfer Network (DTN) [28] is one of the early attempts in the deep HDA area, which constructs multiple weakly-shared layers in the neural networks.…”

Section: Related Workmentioning

confidence: 99%

Prototype-Matching Graph Network for Heterogeneous Domain Adaptation

Wang

Luo

Huang

et al. 2020

Proceedings of the 28th ACM International Conference on Multimedia

View full text Add to dashboard Cite

Even though the multimedia data is ubiquitous on the web, the scarcity of the annotated data and variety of data modalities hinder their usage by multimedia applications. Heterogeneous domain adaptation (HDA) has therefore arisen to address such limitations by facilitating the knowledge transfer between heterogeneous domains. Existing HDA methods only focus on aligning the crossdomain feature distributions and ignore the importance of maximizing the margin among different classes, which may lead to a suboptimal classification performance. To tackle this problem, in this paper, we propose the Prototype-Matching Graph Network (PMGN), which gradually explores the domain-invariant class prototype representations. Specifically, we build an end-to-end Graph Prototypical Network, which computes the class prototypes through multiple layers of edge learning, node aggregation, and discrepancy minimization. Our framework utilizes the Swap training strategy to provide adequate supervision for training the edge learning component. Moreover, the proposed PMGN can be equipped with the clustering module that utilises the KL-divergence as a distance metric to reduce the distribution difference between the source and target data. Extensive experiments on three HDA tasks (i.e. object recognition, text-to-image classification, and text categorization) demonstrate the superiority of our approach over the state-of-theart HDA methods. CCS CONCEPTS • Computing methodologies → Transfer learning.

show abstract

“…GAM (Stretcu et al 2019) uses an agreement model that calculates the probability of two nodes sharing the same label on the graph. EGNN (Kim et al 2019) adapts a deep neural network to predict the edge-labels rather than the node-labels on the graph. However, most of these methods are not suitable for online learning, because they need predefined topological information or whole training data repeatedly.…”

Section: Related Workmentioning

confidence: 99%

Label Propagation Adaptive Resonance Theory for Semi-Supervised Continuous Learning

Kim

Hwang

Kang

et al. 2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Semi-supervised learning and continuous learning are fundamental paradigms for human-level intelligence. To deal with real-world problems where labels are rarely given and the opportunity to access the same data is limited, it is necessary to apply these two paradigms in a joined fashion. In this paper, we propose Label Propagation Adaptive Resonance Theory (LPART) for semi-supervised continuous learning. LPART uses an online label propagation mechanism to perform classification and gradually improves its accuracy as the observed data accumulates. We evaluated the proposed model on visual (MNIST, SVHN, CIFAR-10) and audio (NSynth) datasets by adjusting the ratio of the labeled and unlabeled data. The accuracies are much higher when both labeled and unlabeled data are used, demonstrating the significant advantage of LPART in environments where the data labels are scarce.

show abstract

Edge-Labeling Graph Neural Network for Few-Shot Learning

Cited by 408 publications

References 13 publications

Multi-Scale Decision Network with Feature Fusion and Weighting for Few-Shot Learning

Multi-Scale Decision Network with Feature Fusion and Weighting for Few-Shot Learning

Prototype-Matching Graph Network for Heterogeneous Domain Adaptation

Label Propagation Adaptive Resonance Theory for Semi-Supervised Continuous Learning

Contact Info

Product

Resources

About