Instance-level Sketch-based Retrieval By Deep Triplet Classification Siamese Network

Abstract

Sketch has been employed as an effective communicative tool to express the abstract and intuitive meanings of object. Recognizing the free-hand sketch drawing is extremely useful in many real-world applications. While content-based sketch recognition has been studied for several decades, the instance-level Sketch-Based Image Retrieval (SBIR) tasks have attracted significant research attention recently. The existing datasets such as QMUL-Chair and QMUL-Shoe, focus on the retrieval tasks of chairs and shoes. However, there are several key limitations in previous instance-level SBIR works. The state-of-the-art works have to heavily rely on the pre-training process, quality of edge maps, multi-cropping testing strategy, and augmenting sketch images. To efficiently solve the instance-level SBIR, we propose a new Deep Triplet Classification Siamese Network (DeepTCNet) which employs DenseNet-169 as the basic feature extractor and is optimized by the triplet loss and classification loss. Criti

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keylu2018instance

Related papers

• Generalisation And Sharing In Triplet Convnets For Sketch Based Visual Search (2016)13.11
• 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
• Semi-heterogeneous Three-way Joint Embedding Network For Sketch-based Image Retrieval (2019)12.47
• Back To The Drawing Board: Rethinking Scene-level Sketch-based Image Retrieval (2025)0.00
• Data-free Sketch-based Image Retrieval (2023)13.17
• Domain-smoothing Network For Zero-shot Sketch-based Image Retrieval (2021)13.92
• A Zero-shot Framework For Sketch-based Image Retrieval (2018)16.49