PTF-SimCM: A Simple Contrastive Model with Polysemous Text Fusion for Visual Similarity Metric

Table 1

Notation list of the proposed method.

Symbol	Description
	Input image
	Textual description of image
	Image augmentation
	Image encoder
	Cross-modal encoder
	The number of cross-modal embeddings
	Multimodal projector module
	Predictor module
	Fused feature
	Metric embedding
	Vector output from predictor
	Stop-gradient operation