Semantically Consistent Multi-view Representation Learning
In this work, we devote ourselves to the challenging task of Unsupervised Multi-view Representation Learning (UMRL), which requires learning a unified feature representation from multiple views in an unsupervised manner. Existing UMRL methods mainly concentrate on the learning process in the feature space while ignoring the valuable semantic information hidden in different views. To address this issue, we propose a novel Semantically Consistent Multi-view Representation Learning (SCMRL), which makes efforts to excavate underlying multi-view semantic consensus information and utilize the information to guide the unified feature representation learning. Specifically, SCMRL consists of a within-view reconstruction module and a unified feature representation learning module, which are elegantly integrated by the contrastive learning strategy to simultaneously align semantic labels of both view-specific feature representations and the learned unified feature representation. In this way, the consensus information in the semantic space can be effectively exploited to constrain the learning process of unified feature representation. Compared with several state-of-the-art algorithms, extensive experiments demonstrate its superiority.
Code (0)
등록된 구현이 없습니다.
Tasks
Contrastive LearningRepresentation LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Disentangling Multi-view Representations Beyond Inductive Bias
Multi-view (or -modality) representation learning aims to understand the relationships between different view representations. Existing methods disentangle multi-view representations into consistent and view-specific rep…
ClusteringInductive BiasRepresentation LearningSpecificityScenePainter: Semantically Consistent Perpetual 3D Scene Generation with Concept Relation Alignment
Perpetual 3D scene generation aims to produce long-range and coherent 3D view sequences, which is applicable for long-term video synthesis and 3D scene reconstruction. Existing methods follow a "navigate-and-imagine" fas…
Scene GenerationSeed the Views: Hierarchical Semantic Alignment for Contrastive Representation Learning
Self-supervised learning based on instance discrimination has shown remarkable progress. In particular, contrastive learning, which regards each image as well as its augmentations as an individual class and tries to dist…
Contrastive LearningLinear evaluationRepresentation LearningSelf-Supervised Image Classification+1C^2M-DoT: Cross-modal consistent multi-view medical report generation with domain transfer network
In clinical scenarios, multiple medical images with different views are usually generated simultaneously, and these images have high semantic consistency. However, most existing medical report generation methods only con…
Contrastive LearningMedical Report GenerationSEMAGIC: Learning Semantically Consistent Deformable 3D Representations from In-the-Wild Images
Learning deformable 3D object models from single-view in-the-wild images has enabled impressive 3D shape reconstruction without supervision. However, it remains unclear whether these models capture the semantic structure…
3D Shape ReconstructionSemantic correspondence