Hyperbolic Visual Embedding Learning for Zero-Shot Recognition

Liu, Shaoteng; Chen, Jingjing; Pan, Liangming; Ngo, Chong‐Wah; Chua, Tat-Seng; Jiang, Yu‐Gang

doi:10.1109/cvpr42600.2020.00929

Cited by 91 publications

(60 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Baselines. The compared baselines include both classical and recent state-of-the-art ZSL methods: DAP [15], ESZSL [22], ZS-GCN [33], WDVSc [30], and Hyperbolic-ZSL [19]. In addition, as traditional methods are mainly designed for computer vision, their original implementations heavily rely on some pre-trained CNNs.…”

Section: Methodsmentioning

confidence: 99%

Zero-shot Node Classification with Decomposed Graph Prototype Network

Wang

Wang²,

Guo

et al. 2021

Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery &Amp; Data Mining

View full text Add to dashboard Cite

Node classification is a central task in graph data analysis. Scarce or even no labeled data of emerging classes is a big challenge for existing methods. A natural question arises: can we classify the nodes from those classes that have never been seen?In this paper, we study this zero-shot node classification (ZNC) problem which has a two-stage nature: (1) acquiring high-quality class semantic descriptions (CSDs) for knowledge transfer, and (2) designing a well generalized graph-based learning model. For the first stage, we give a novel quantitative CSDs evaluation strategy based on estimating the real class relationships, to get the "best" CSDs in a completely automatic way. For the second stage, we propose a novel Decomposed Graph Prototype Network (DGPN) method, following the principles of locality and compositionality for zero-shot model generalization. Finally, we conduct extensive experiments to demonstrate the effectiveness of our solutions. CCS CONCEPTS• Information systems → Data mining; • Mathematics of computing → Graph theory; • Computing methodologies → Machine learning.

show abstract

Section: Methodsmentioning

confidence: 99%

Zero-shot Node Classification with Decomposed Graph Prototype Network

Wang

Wang²,

Guo

et al. 2021

Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery &Amp; Data Mining

View full text Add to dashboard Cite

show abstract

“…Here, we consider a stronger version, DeViSE , in which we model f θ and g φ each by a two-hidden layers multi-layer perceptron (MLP). We also experiment with two state-of-the-art ZSL algorithms, EXEM (Changpinyo et al, 2020) and HVE (Liu et al, 2020).…”

Section: Baselines Variants and Metricsmentioning

confidence: 99%

“…Compared to the average per-sample accuracy, the per-class accuracy is a more suitable for ImageNet since the dataset is highly imbalanced (Changpinyo et al, 2020). The state-of-theart algorithms in ZSL are EXEM and HVE proposed by (Changpinyo et al, 2020) and (Liu et al, 2020), respectively. To make fair comparison with our models, we evaluate their algorithms on the same number of our test classes using their official codes.…”

Section: E Dataset Features Metrics and Zsl Algorithmmentioning

confidence: 99%

See 1 more Smart Citation

Revisiting Document Representations for Large-Scale Zero-Shot Learning

Kil¹,

Chao²

2021

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

Zero-shot learning aims to recognize unseen objects using their semantic representations. Most existing works use visual attributes labeled by humans, not suitable for large-scale applications. In this paper, we revisit the use of documents as semantic representations. We argue that documents like Wikipedia pages contain rich visual information, which however can easily be buried by the vast amount of non-visual sentences. To address this issue, we propose a semi-automatic mechanism for visual sentence extraction that leverages the document section headers and the clustering structure of visual sentences. The extracted visual sentences, after a novel weighting scheme to distinguish similar classes, essentially form semantic representations like visual attributes but need much less human effort. On the Ima-geNet dataset with over 10,000 unseen classes, our representations lead to a 64% relative improvement against the commonly used ones.

show abstract

“…Using these analyses, [19] added a single layer of hyperbolic neural networks [11] to deep convolutional networks and showed the benefits of hyperbolic embeddings on few-shot learning and person re-identification. Another work [28] also demonstrated the suitability of hyperbolic embeddings on zero-shot learning. However, most of the existing hyperbolic representation learning works [19,28,5,27,1] mainly focus on a supervised setting, and the effect of hyperbolic geometry on unsupervised representation learning has not been explored deeply so far [32,15,36].…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Hyperbolic Representation Learning via Message Passing Auto-Encoders

Park

Cho

Chang

et al. 2021

2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

Most of the existing literature regarding hyperbolic embedding concentrate upon supervised learning, whereas the use of unsupervised hyperbolic embedding is less well explored. In this paper, we analyze how unsupervised tasks can benefit from learned representations in hyperbolic space. To explore how well the hierarchical structure of unlabeled data can be represented in hyperbolic spaces, we design a novel hyperbolic message passing auto-encoder whose overall auto-encoding is performed in hyperbolic space. The proposed model conducts auto-encoding the networks via fully utilizing hyperbolic geometry in message passing. Through extensive quantitative and qualitative analyses, we validate the properties and benefits of the unsupervised hyperbolic representations. Codes are available at https://github.com/junhocho/HGCAE.

show abstract

Hyperbolic Visual Embedding Learning for Zero-Shot Recognition

Cited by 91 publications

References 24 publications

Zero-shot Node Classification with Decomposed Graph Prototype Network

Zero-shot Node Classification with Decomposed Graph Prototype Network

Revisiting Document Representations for Large-Scale Zero-Shot Learning

Unsupervised Hyperbolic Representation Learning via Message Passing Auto-Encoders

Contact Info

Product

Resources

About