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

## TL;DR

This paper introduces a CCA-based neural network layer that improves cross-modality retrieval by combining optimal correlation projections with pairwise ranking losses, demonstrating superior performance across multiple retrieval scenarios especially with limited training data.

## Contribution

The paper presents the CCA Layer (CCAL), a novel neural network component that analytically computes optimal projections for better embedding spaces in cross-modality retrieval tasks.

## Key findings

- Outperforms Deep CCA and multi-view networks in retrieval tasks.
- Effective especially with limited training data.
- Applicable to text-to-image, audio-sheet-music, and zero-shot retrieval.

## 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 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).