Contrastive Learning and the Emergence of Attributes Associations
원문 초록
In response to an object presentation, supervised learning schemes generally respond with a parsimonious label. Upon a similar presentation we humans respond again with a label, but are flooded, in addition, by a myriad of associations. A significant portion of these consist of the presented object attributes. Contrastive learning is a semi-supervised learning scheme based on the application of identity preserving transformations on the object input representations. It is conjectured in this work that these same applied transformations preserve, in addition to the identity of the presented object, also the identity of its semantically meaningful attributes. The corollary of this is that the output representations of such a contrastive learning scheme contain valuable information not only for the classification of the presented object, but also for the presence or absence decision of any attribute of interest. Simulation results which demonstrate this idea and the feasibility of this conjecture are presented.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Multiple Object Stitching for Unsupervised Representation Learning
DreamGrasp: Zero-Shot 3D Multi-Object Reconstruction from Partial-View Images for Robotic Manipulation
Helping CLIP See Both the Forest and the Trees: A Decomposition and Description Approach
FOCUS: Fine-grained Optimization with Semantic Guided Understanding for Pedestrian Attributes Recognition
Hypergraph Contrastive Learning for Drug Trafficking Community Detection
Multi-modal Siamese Network for Entity Alignment
토론
이 논문과 연결된 포럼 글이 아직 없습니다.