Weakly Supervised Disentanglement by Pairwise Similarities
Recently, researches related to unsupervised disentanglement learning with deep generative models have gained substantial popularity. However, without introducing supervision, there is no guarantee that the factors of interest can be successfully recovered. Motivated by a real-world problem, we propose a setting where the user introduces weak supervision by providing similarities between instances based on a factor to be disentangled. The similarity is provided as either a binary (yes/no) or a real-valued label describing whether a pair of instances are similar or not. We propose a new method for weakly supervised disentanglement of latent variables within the framework of Variational Autoencoder. Experimental results demonstrate that utilizing weak supervision improves the performance of the disentanglement method substantially.
Code (1)
Tasks
DisentanglementSimilar Papers 제목 키워드 기반
Pairwise Similarity Knowledge Transfer for Weakly Supervised Object Localization
Weakly Supervised Object Localization (WSOL) methods only require image level labels as opposed to expensive bounding box annotations required by fully supervised algorithms. We study the problem of learning localization…
Object LocalizationTransfer LearningWeakly-Supervised Object LocalizationKnowledge-guided Pairwise Reconstruction Network for Weakly Supervised Referring Expression Grounding
Weakly supervised referring expression grounding (REG) aims at localizing the referential entity in an image according to linguistic query, where the mapping between the image region (proposal) and the query is unknown i…
ObjectReferring ExpressionRegion ProposalWeakly-supervised LearningUnderstanding and Guiding Weakly Supervised Entity Alignment with Potential Isomorphism Propagation
Weakly Supervised Entity Alignment (EA) is the task of identifying equivalent entities across diverse knowledge graphs (KGs) using only a limited number of seed alignments. Despite substantial advances in aggregation-bas…
Entity AlignmentKnowledge GraphsSW-VAE: Weakly Supervised Learn Disentangled Representation Via Latent Factor Swapping
Representation disentanglement is an important goal of representation learning that benefits various downstream tasks. To achieve this goal, many unsupervised learning representation disentanglement approaches have been …
DisentanglementRepresentation LearningClassification from Pairwise Similarities/Dissimilarities and Unlabeled Data via Empirical Risk Minimization
Pairwise similarities and dissimilarities between data points might be easier to obtain than fully labeled data in real-world classification problems, e.g., in privacy-aware situations. To handle such pairwise informatio…
ClusteringGeneral Classification