Litcius/Paper detail

Learnable Pillar-based Re-ranking for Image-Text Retrieval

Leigang Qu, Meng Liu, Wenjie Wang, Zhedong Zheng, Liqiang Nie, Tat‐Seng Chua

202321 citationsDOIOpen Access PDF

Abstract

Image-text retrieval aims to bridge the modality gap and retrieve cross-modal content based on semantic similarities. Prior work usually focuses on the pairwise relations (i.e., whether a data sample matches another) but ignores the higher-order neighbor relations (i.e., a matching structure among multiple data samples). Re-ranking, a popular post-processing practice, has revealed the superiority of capturing neighbor relations in single-modality retrieval tasks. However, it is ineffective to directly extend existing re-ranking algorithms to image-text retrieval. In this paper, we analyze the reason from four perspectives, i.e., generalization, flexibility, sparsity, and asymmetry, and propose a novel learnable pillar-based re-ranking paradigm. Concretely, we first select top-ranked intra- and intermodal neighbors as pillars, and then reconstruct data samples with the neighbor relations between them and the pillars. In this way, each sample can be mapped into a multimodal pillar space only using similarities, ensuring generalization. After that, we design a neighbor-aware graph reasoning module to flexibly exploit the relations and excavate the sparse positive items within a neighborhood. We also present a structure alignment constraint to promote crossmodal collaboration and align the asymmetric modalities. On top of various base backbones, we carry out extensive experiments on two benchmark datasets, i.e., Flickr30K and MS-COCO, demonstrating the effectiveness, superiority, generalization, and transferability of our proposed re-ranking paradigm.

Topics & Concepts

Computer scienceArtificial intelligenceRanking (information retrieval)Learning to rankExploitPairwise comparisonInformation retrievalBenchmark (surveying)GeneralizationImage retrievalPattern recognition (psychology)Machine learningData miningNatural language processingImage (mathematics)MathematicsMathematical analysisGeodesyGeographyComputer securityMultimodal Machine Learning ApplicationsAdvanced Image and Video Retrieval TechniquesDomain Adaptation and Few-Shot Learning
Learnable Pillar-based Re-ranking for Image-Text Retrieval | Litcius