CVDec 11, 2023

Dynamic Weighted Combiner for Mixed-Modal Image Retrieval

arXiv:2312.06179v129 citationsh-index: 9Has CodeAAAI
Originality Incremental advance
AI Analysis

This work improves retrieval accuracy for users in mixed-modal search scenarios, representing a strong specific gain rather than a foundational advancement.

The paper tackles the problem of limited performance in Mixed-Modal Image Retrieval (MMIR) by addressing unequal modality contributions and labeling noises, resulting in a model that significantly outperforms state-of-the-art methods on real-world datasets.

Mixed-Modal Image Retrieval (MMIR) as a flexible search paradigm has attracted wide attention. However, previous approaches always achieve limited performance, due to two critical factors are seriously overlooked. 1) The contribution of image and text modalities is different, but incorrectly treated equally. 2) There exist inherent labeling noises in describing users' intentions with text in web datasets from diverse real-world scenarios, giving rise to overfitting. We propose a Dynamic Weighted Combiner (DWC) to tackle the above challenges, which includes three merits. First, we propose an Editable Modality De-equalizer (EMD) by taking into account the contribution disparity between modalities, containing two modality feature editors and an adaptive weighted combiner. Second, to alleviate labeling noises and data bias, we propose a dynamic soft-similarity label generator (SSG) to implicitly improve noisy supervision. Finally, to bridge modality gaps and facilitate similarity learning, we propose a CLIP-based mutual enhancement module alternately trained by a mixed-modality contrastive loss. Extensive experiments verify that our proposed model significantly outperforms state-of-the-art methods on real-world datasets. The source code is available at \url{https://github.com/fuxianghuang1/DWC}.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes