Domain-aware SE Network For Sketch-based Image Retrieval With Multiplicative Euclidean Margin Softmax

Abstract

This paper proposes a novel approach for Sketch-Based Image Retrieval (SBIR), for which the key is to bridge the gap between sketches and photos in terms of the data representation. Inspired by channel-wise attention explored in recent years, we present a Domain-Aware Squeeze-and-Excitation (DASE) network, which seamlessly incorporates the prior knowledge of sample sketch or photo into SE module and make the SE module capable of emphasizing appropriate channels according to domain signal. Accordingly, the proposed network can switch its mode to achieve a better domain feature with lower intra-class discrepancy. Moreover, while previous works simply focus on minimizing intra-class distance and maximizing inter-class distance, we introduce a loss function, named Multiplicative Euclidean Margin Softmax (MEMS), which introduces multiplicative Euclidean margin into feature space and ensure that the maximum intra-class distance is smaller than the minimum inter-class distance. This facilitat

Stats

• citations11
• S2 citations—
• github stars0
• HF likes0
• heat score8.09
• arxiv keylu2018domain

Related papers

• Domain-smoothing Network For Zero-shot Sketch-based Image Retrieval (2021)13.92
• Semi-heterogeneous Three-way Joint Embedding Network For Sketch-based Image Retrieval (2019)12.47
• Cross-modal Subspace Learning For Fine-grained Sketch-based Image Retrieval (2017)13.34
• Towards Unsupervised Sketch-based Image Retrieval (2021)0.00
• Relation-aware Meta-learning For Zero-shot Sketch-based Image Retrieval (2024)0.00
• Bda-sketret: Bi-level Domain Adaptation For Zero-shot SBIR (2022)10.35
• Semantic Adversarial Network For Zero-shot Sketch-based Image Retrieval (2019)10.74
• Acnet: Approaching-and-centralizing Network For Zero-shot Sketch-based Image Retrieval (2021)10.74