# End-to-End Cross-Modality Retrieval with CCA Projections and Pairwise Ranking Loss

arXiv: https://arxiv.org/abs/1705.06979 · HTML: https://mlsanity.com/paper/1705.06979/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 May 2017.

## Built on by (most cited first, 7 of 7)

- [Content-Based Medical Image Retrieval with Opponent Class Adaptive Margin Loss](https://mlsanity.com/paper/2211.15371/) (2022)
- [Complete Cross-triplet Loss in Label Space for Audio-visual Cross-modal Retrieval](https://mlsanity.com/paper/2211.03434/) (2022)
- [Self-Supervised Contrastive Learning for Robust Audio-Sheet Music Retrieval Systems](https://mlsanity.com/paper/2309.12134/) (2023)
- [Towards Robust and Truly Large-Scale Audio-Sheet Music Retrieval](https://mlsanity.com/paper/2309.12158/) (2023)
- [Dynamically-Scaled Deep Canonical Correlation Analysis](https://mlsanity.com/paper/2203.12377/) (2022)
- [Passage Summarization with Recurrent Models for Audio-Sheet Music Retrieval](https://mlsanity.com/paper/2309.12111/) (2023)
- [When Does Dense Retrieval Need Asymmetric Geometry? A Bias-Variance Theory of Shared and Dual Projections](https://mlsanity.com/paper/2609.32488/) (2026)

## Abstract (arXiv)

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 freely learned projections optimized by a pairwise ranking loss, especially when little training data is available (the code for all three methods is released at: https://github.com/CPJKU/cca_layer).