Existing methods for asymmetric image retrieval employ a rigid pairwise similarity constraint
between the query network and the larger gallery network. However these one-to-one …

Asymmetric image retrieval, which typically uses small model for query side and large model
for database server, is an effective solution for resource-constrained scenarios. However …

In asymmetric retrieval systems, models with different capacities are deployed on platforms
with different computational and storage resources. Despite the great progress, existing …

Learning compatible representations enables the interchangeable use of semantic features
as models are updated over time. This is particularly relevant in search and retrieval systems …

Image retrieval plays an important role in the Internet world. Usually, the core parts of
mainstream visual retrieval systems include an online service of the embedding model and …

Visual retrieval aims to search for the most relevant visual items, eg, images and videos,
from a candidate gallery with a given query item. Accuracy and efficiency are two competing …

Asymmetric image retrieval is a task that seeks to balance retrieval accuracy and efficiency
by leveraging lightweight and large models for the query and gallery sides, respectively. The …

Large-scale embedding-based retrieval (EBR) is the cornerstone of search-related industrial
applications. Given a user query, the system of EBR aims to identify relevant information …

Open-world visual recognition aims to empower models to identify objects in real-world
settings, particularly when they encounter domains or categories that are not included in the …

Deep metric learning for vision is trained by optimizing a representation network to map (non-
) matching image pairs to (non-) similar representations. During testing, which typically …