Domain-smoothing Network For Zero-shot Sketch-based Image Retrieval

Abstract

Zero-Shot Sketch-Based Image Retrieval (ZS-SBIR) is a novel cross-modal retrieval task, where abstract sketches are used as queries to retrieve natural images under zero-shot scenario. Most existing methods regard ZS-SBIR as a traditional classification problem and employ a cross-entropy or triplet-based loss to achieve retrieval, which neglect the problems of the domain gap between sketches and natural images and the large intra-class diversity in sketches. Toward this end, we propose a novel Domain-Smoothing Network (DSN) for ZS-SBIR. Specifically, a cross-modal contrastive method is proposed to learn generalized representations to smooth the domain gap by mining relations with additional augmented samples. Furthermore, a category-specific memory bank with sketch features is explored to reduce intra-class diversity in the sketch domain. Extensive experiments demonstrate that our approach notably outperforms the state-of-the-art methods in both Sketchy and TU-Berlin datasets. Our sour

Stats

• citations36
• S2 citations—
• github stars11
• HF likes0
• heat score13.92
• arxiv keywang2021domain

Related papers

• Semantic Adversarial Network For Zero-shot Sketch-based Image Retrieval (2019)10.74
• Stacked Semantic-guided Network For Zero-shot Sketch-based Image Retrieval (2019)0.00
• An Efficient Framework For Zero-shot Sketch-based Image Retrieval (2021)13.65
• Relation-aware Meta-learning For Zero-shot Sketch-based Image Retrieval (2024)0.00
• Stacked Adversarial Network For Zero-shot Sketch Based Image Retrieval (2020)10.74
• Ontology-aware Network For Zero-shot Sketch-based Image Retrieval (2023)6.34
• Bda-sketret: Bi-level Domain Adaptation For Zero-shot SBIR (2022)10.35
• Three-stream Joint Network For Zero-shot Sketch-based Image Retrieval (2022)0.00