Partial Transfer Learning with Selective Adversarial Networks

Cao, Zhangjie; Long, Mingsheng; Wang, Jianmin; Jordan, Michael I.

doi:10.1109/cvpr.2018.00288

Cited by 357 publications

(318 citation statements)

References 16 publications

Supporting

Mentioning

317

Contrasting

Order By: Relevance

“…The task is to classify all samples in T including known and unknown categories, which is undoubtedly a more chal- * Corresponding author. lenging task but closer to the case in real-world applications compared to other related tasks in Domain Adaptation (DA) [2,3,4,20,21,33,40,42,34,13,5,10,25] and Zero-Shot Learning (ZSL) [24,11,28,16,32,15,14,29,41].…”

Section: Introductionmentioning

confidence: 94%

Unsupervised Open Domain Recognition by Semantic Discrepancy Minimization

Zhuo

Wang²,

Cui

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

We address the unsupervised open domain recognition (UODR) problem, where categories in labeled source domain S is only a subset of those in unlabeled target domain T . The task is to correctly classify all samples in T including known and unknown categories. UODR is challenging due to the domain discrepancy, which becomes even harder to bridge when a large number of unknown categories exist in T . Moreover, the classification rules propagated by graph CNN (GCN) may be distracted by unknown categories and lack generalization capability.To measure the domain discrepancy for asymmetric label space between S and T , we propose Semantic-Guided Matching Discrepancy (SGMD), which first employs instance matching between S and T , and then the discrepancy is measured by a weighted feature distance between matched instances. We further design a limited balance constraint to achieve a more balanced classification output on known and unknown categories. We develop Unsupervised Open Domain Transfer Network (UODTN), which learns both the backbone classification network and GCN jointly by reducing the SGMD, enforcing the limited balance constraint and minimizing the classification loss on S. UODTN better preserves the semantic structure and enforces the consistency between the learned domain invariant visual features and the semantic embeddings. Experimental results show superiority of our method on recognizing images of both known and unknown categories.

show abstract

Section: Introductionmentioning

confidence: 94%

Unsupervised Open Domain Recognition by Semantic Discrepancy Minimization

Zhuo

Wang²,

Cui

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

show abstract

“…Generative adversarial nets (GANs) [13] have become a popular solution to reduce domain discrepancy through an adversarial objective concerning a domain classifier [12,33,39]. Recently, only a few domain adaptation algorithms [4,7] that can handle imbalanced relation distribution or partial adaptation have been proposed. [5] proposed a method to simultaneously alleviate negative transfer by down-weighting the data of outlier source classes in category level.…”

Section: Related Workmentioning

confidence: 99%

Relation Adversarial Network for Low Resource Knowledge Graph Completion

Zhang

Deng

Sun

et al. 2020

Proceedings of the Web Conference 2020

View full text Add to dashboard Cite

Knowledge Graph Completion (KGC) has been proposed to improve Knowledge Graphs by filling in missing connections via link prediction or relation extraction. One of the main difficulties for KGC is a low resource problem. Previous approaches assume sufficient training triples to learn versatile vectors for entities and relations, or a satisfactory number of labeled sentences to train a competent relation extraction model. However, low resource relations are very common in KGs, and those newly added relations often do not have many known samples for training. In this work, we aim at predicting new facts under a challenging setting where only limited training instances are available. We propose a general framework called Weighted Relation Adversarial Network, which utilizes an adversarial procedure to help adapt knowledge/features learned from high resource relations to different but related low resource relations. Specifically, the framework takes advantage of a relation discriminator to distinguish between samples from different relations, and help learn relation-invariant features more transferable from source relations to target relations. Experimental results show that the proposed approach outperforms previous methods regarding low resource settings for both link prediction and relation extraction.

show abstract

“…Another adversarial discriminator based model is [34], where multiple discriminators (MADA) have been used to solve the mode collapse problem in the domain adaptation. Some works closely related to MADA have been proposed in [4,3]. The labeled discriminator [23] used to tackle the mode collapse problem in domain adaptation.…”

Section: Literature Surveymentioning

confidence: 99%

Attending to Discriminative Certainty for Domain Adaptation

Kurmi

Kumar

Namboodiri

2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

In this paper, we aim to solve for unsupervised domain adaptation of classifiers where we have access to label information for the source domain while these are not available for a target domain. While various methods have been proposed for solving these including adversarial discriminator based methods, most approaches have focused on the entire image based domain adaptation. In an image, there would be regions that can be adapted better, for instance, the foreground object may be similar in nature. To obtain such regions, we propose methods that consider the probabilistic certainty estimate of various regions and specify focus on these during classification for adaptation. We observe that just by incorporating the probabilistic certainty of the discriminator while training the classifier, we are able to obtain state of the art results on various datasets as compared against all the recent methods. We provide a thorough empirical analysis of the method by providing ablation analysis, statistical significance test, and visualization of the attention maps and t-SNE embeddings. These evaluations convincingly demonstrate the effectiveness of the proposed approach.

show abstract

Partial Transfer Learning with Selective Adversarial Networks

Cited by 357 publications

References 16 publications

Unsupervised Open Domain Recognition by Semantic Discrepancy Minimization

Unsupervised Open Domain Recognition by Semantic Discrepancy Minimization

Relation Adversarial Network for Low Resource Knowledge Graph Completion

Attending to Discriminative Certainty for Domain Adaptation

Contact Info

Product

Resources

About