A Recipe For Efficient SBIR Models: Combining Relative Triplet Loss With Batch Normalization And Knowledge Distillation

Abstract

Sketch-Based Image Retrieval (SBIR) is a crucial task in multimedia retrieval, where the goal is to retrieve a set of images that match a given sketch query. Researchers have already proposed several well-performing solutions for this task, but most focus on enhancing embedding through different approaches such as triplet loss, quadruplet loss, adding data augmentation, and using edge extraction. In this work, we tackle the problem from various angles. We start by examining the training data quality and show some of its limitations. Then, we introduce a Relative Triplet Loss (RTL), an adapted triplet loss to overcome those limitations through loss weighting based on anchors similarity. Through a series of experiments, we demonstrate that replacing a triplet loss with RTL outperforms previous state-of-the-art without the need for any data augmentation. In addition, we demonstrate why batch normalization is more suited for SBIR embeddings than l2-normalization and show that it improves s

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyseddati2023a

Related papers

• Exploiting Unlabelled Photos For Stronger Fine-grained SBIR (2023)10.61
• Relation-aware Meta-learning For Zero-shot Sketch-based Image Retrieval (2024)0.00
• A Zero-shot Framework For Sketch-based Image Retrieval (2018)16.49
• Data-free Sketch-based Image Retrieval (2023)13.17
• Generative Model For Zero-shot Sketch-based Image Retrieval (2019)9.23
• Towards Unsupervised Sketch-based Image Retrieval (2021)0.00
• Generalisation And Sharing In Triplet Convnets For Sketch Based Visual Search (2016)13.11
• Instance-level Sketch-based Retrieval By Deep Triplet Classification Siamese Network (2018)0.00