End-to-end Cross-modality Retrieval With CCA Projections And Pairwise Ranking Loss

Abstract

Cross-modality retrieval encompasses retrieval tasks where the fetched items are of a different type than the search query, e.g., retrieving pictures relevant to a given text query. The state-of-the-art approach to cross-modality retrieval relies on learning a joint embedding space of the two modalities, where items from either modality are retrieved using nearest-neighbor search. In this work, we introduce a neural network layer based on Canonical Correlation Analysis (CCA) that learns better embedding spaces by analytically computing projections that maximize correlation. In contrast to previous approaches, the CCA Layer (CCAL) allows us to combine existing objectives for embedding space learning, such as pairwise ranking losses, with the optimal projections of CCA. We show the effectiveness of our approach for cross-modality retrieval on three different scenarios (text-to-image, audio-sheet-music and zero-shot retrieval), surpassing both Deep CCA and a multi-view network using freel

Stats

• citations35
• S2 citations—
• github stars31
• HF likes0
• heat score14.68
• arxiv keydorfer2017end

Related papers

• Variational Autoencoder With CCA For Audio-visual Cross-modal Retrieval (2021)9.92
• Deep Triplet Neural Networks With Cluster-cca For Audio-visual Cross-modal Retrieval (2019)12.61
• Audio-visual Embedding For Cross-modal Musicvideo Retrieval Through Supervised Deep CCA (2019)11.93
• Learning Joint Embedding For Cross-modal Retrieval (2019)5.84
• Cross-modal Center Loss (2020)0.00
• Revisiting Cross Modal Retrieval (2018)0.00
• Cross-modal Coordination Across A Diverse Set Of Input Modalities (2024)0.00
• Adversarial Cross-modal Retrieval Via Learning And Transferring Single-modal Similarities (2019)8.60