Cooperative Embeddings For Instance, Attribute And Category Retrieval

Abstract

The goal of this paper is to retrieve an image based on instance, attribute and category similarity notions. Different from existing works, which usually address only one of these entities in isolation, we introduce a cooperative embedding to integrate them while preserving their specific level of semantic representation. An algebraic structure defines a superspace filled with instances. Attributes are axis-aligned to form subspaces, while categories influence the arrangement of similar instances. These relationships enable them to cooperate for their mutual benefits for image retrieval. We derive a proxy-based softmax embedding loss to learn simultaneously all similarity measures in both superspace and subspaces. We evaluate our model on datasets from two different domains. Experiments on image retrieval tasks show the benefits of the cooperative embeddings for modeling multiple image similarities, and for discovering style evolution of instances between- and within-categories.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keythong2019cooperative

Related papers

• Learning To Embed Semantic Similarity For Joint Image-text Retrieval (2022)7.50
• Image Search Using Multilingual Texts: A Cross-modal Learning Approach Between Image And Text (2019)0.00
• Improving Cross-modal Retrieval With Set Of Diverse Embeddings (2022)13.55
• Bundle Optimization For Multi-aspect Embedding (2017)0.00
• Probabilistic Embeddings For Cross-modal Retrieval (2021)21.70
• Unsupervised Embedding Learning Via Invariant And Spreading Instance Feature (2019)19.76
• Aligning Multilingual Word Embeddings For Cross-modal Retrieval Task (2019)2.26
• Polysemous Visual-semantic Embedding For Cross-modal Retrieval (2019)17.70