Attribute Propagation Network for Graph Zero-Shot Learning

Liu, Lu; Zhou, Tianyi; Long, Guodong; Jiang, Jing; Zhang, Chengqi

doi:10.1609/aaai.v34i04.5923

Cited by 69 publications

(44 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed two HarS based inductive methods, HarS-WGAN and HarS-VAEGAN are compared with 18 stateof-the-art inductive methods: DEVISE [4], LATEM [17], SAE [49], DEM [22], LiGAN [28], ABP [30], TCN [24], OCD-GZSL [50], APNet [51], DE-VAE [52], LsrGAN [53], f-CSLWGAN [11], DASCN [27], DVBE [9], DAZLE [54], TF-VAEGAN [13], CF-GZSL [19], GCM-CF [37]. The proposed two HarST based transductive methods, HarST-DEM and HarST-WGAN are compared with 14 state-ofthe-art transductive methods: ALE-tran [16], GFZSL [55], DSRL [56], QFSL [40], GMN [57], f-VAEGAN-D2 [44], GXE [42], SABR-T [29], PREN [41], VSC [58], DTN [59], ADA [60], SDGN [45], TF-VAEGAN [13].…”

Section: Datasets and Comparative Methodsmentioning

confidence: 99%

HardBoost: Boosting Zero-Shot Learning with Hard Classes

Liu¹,

Hu²,

Hu³

et al. 2022

Preprint

View full text Add to dashboard Cite

This work is a systematical analysis on the so-called hard class problem in zero-shot learning (ZSL), that is, some unseen classes disproportionally affect the ZSL performances than others, as well as how to remedy the problem by detecting and exploiting hard classes. At first, we report our empirical finding that the hard class problem is a ubiquitous phenomenon and persists regardless of used specific methods in ZSL. Then, we find that high semantic affinity among unseen classes is a plausible underlying cause of hardness and design two metrics to detect hard classes. Finally, two frameworks are proposed to remedy the problem by detecting and exploiting hard classes, one under inductive setting, the other under transductive setting. The proposed frameworks could accommodate most existing ZSL methods to further significantly boost their performances with little efforts. Extensive experiments on three popular benchmarks demonstrate the benefits by identifying and exploiting the hard classes in ZSL.

show abstract

Section: Datasets and Comparative Methodsmentioning

confidence: 99%

HardBoost: Boosting Zero-Shot Learning with Hard Classes

Liu¹,

Hu²,

Hu³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Also, other applications like pose estimation [35] and segmentation [36] or other image sources like videos or sketches [37] are excluded. Topics like few-shot or zero-shot learning methods such as [38] are excluded in this survey. However, we will see in subsection IV-D that topics like few-shot learning and semi-supervised can learn from each other in the future like in [39].…”

Section: A Related Workmentioning

confidence: 99%

“…We conclude that on datasets with few and a fixed number of classes semi-supervised methods will be more important than unsupervised methods. However, if we have a lot of classes or new classes should be detected like in few-or zeroshot learning [38], [94], [99], [100] unsupervised methods will still have a lower labeling cost and be of high importance. This means future research has to investigate how the semi-supervised ideas can be transferred to unsupervised methods as in [14], [41] and to settings with many, an unknown or rising amount of classes like in [39], [96].…”

Section: Trend: How Much Supervision Is Needed?mentioning

confidence: 99%

A Survey on Semi-, Self- and Unsupervised Learning for Image Classification

et al. 2021

View full text Add to dashboard Cite

While deep learning strategies achieve outstanding results in computer vision tasks, one issue remains: The current strategies rely heavily on a huge amount of labeled data. In many real-world problems, it is not feasible to create such an amount of labeled training data. Therefore, it is common to incorporate unlabeled data into the training process to reach equal results with fewer labels. Due to a lot of concurrent research, it is difficult to keep track of recent developments. In this survey, we provide an overview of often used ideas and methods in image classification with fewer labels. We compare 34 methods in detail based on their performance and their commonly used ideas rather than a fine-grained taxonomy. In our analysis, we identify three major trends that lead to future research opportunities. 1. State-of-the-art methods are scaleable to real-world applications in theory but issues like class imbalance, robustness, or fuzzy labels are not considered. 2. The degree of supervision which is needed to achieve comparable results to the usage of all labels is decreasing and therefore methods need to be extended to settings with a variable number of classes. 3. All methods share some common ideas but we identify clusters of methods that do not share many ideas. We show that combining ideas from different clusters can lead to better performance.

show abstract

“…In this way, the student model gets feedback from its teacher and retrains with the high-quality data generated by itself. Dong et al [46] proposed an Isometric Propagation Network (IPN) method, which learned to generate the vision feature with semantic information for unlabeled data/unseen classes.…”

Section: Quality Of Pseudo Labelsmentioning

confidence: 99%

Asymmetric Mutual Mean-Teaching for Unsupervised Domain Adaptive Person Re-Identification

Dong

Liu

2021

IEEE Access

View full text Add to dashboard Cite

Unsupervised domain adaptive person re-identification aims to solve the problem of poor performance caused by transferring an unlabeled target domain from the labeled source domain in the reidentification task. The clustering pseudo-labels method in unsupervised learning is widely used in unsupervised adaptive person re-identification tasks, and it maintains state-of-the-art performance. However, pseudo-labels obtained through clustering often have much noise, and the use of a single network model structure and a single clustering algorithm can easily cause model learning to stagnate, making the model not generalizable. To solve this problem, this paper proposes an asymmetric mutual mean-teaching method for unsupervised adaptive person re-identification. In terms of feature extraction, two asymmetric network models with different structures are used for mutual mean-teaching on the target domain, making the features extracted by the network more robust. In terms of feature clustering, two clustering methods are used for mutual teaching to dynamically update the centroid of clusters to improve the confidence of clustering pseudo-labels. Finally, the triplet loss is improved based on the updated cluster centroid to improve the clustering effect. The proposed method is used to perform a large number of verification experiments on three public datasets. The experimental results show that the proposed method has better accuracy than other unsupervised person re-identification based on clustering pseudo-labels.INDEX TERMS Deep learning, person re-identification, unsupervised domain adaptation, mutual meanteaching.

show abstract

Attribute Propagation Network for Graph Zero-Shot Learning

Cited by 69 publications

References 45 publications

HardBoost: Boosting Zero-Shot Learning with Hard Classes

HardBoost: Boosting Zero-Shot Learning with Hard Classes

A Survey on Semi-, Self- and Unsupervised Learning for Image Classification

Asymmetric Mutual Mean-Teaching for Unsupervised Domain Adaptive Person Re-Identification

Contact Info

Product

Resources

About