Sketchmate: Deep Hashing For Million-scale Human Sketch Retrieval

Abstract

We propose a deep hashing framework for sketch retrieval that, for the first time, works on a multi-million scale human sketch dataset. Leveraging on this large dataset, we explore a few sketch-specific traits that were otherwise under-studied in prior literature. Instead of following the conventional sketch recognition task, we introduce the novel problem of sketch hashing retrieval which is not only more challenging, but also offers a better testbed for large-scale sketch analysis, since: (i) more fine-grained sketch feature learning is required to accommodate the large variations in style and abstraction, and (ii) a compact binary code needs to be learned at the same time to enable efficient retrieval. Key to our network design is the embedding of unique characteristics of human sketch, where (i) a two-branch CNN-RNN architecture is adapted to explore the temporal ordering of strokes, and (ii) a novel hashing loss is specifically designed to accommodate both the temporal and abstrac

Stats

• citations100
• S2 citations—
• github stars0
• HF likes0
• heat score15.03
• arxiv keyxu2018sketchmate

Related papers

• On Learning Semantic Representations For Million-scale Free-hand Sketches (2020)0.00
• Deep Sketch Hashing: Fast Free-hand Sketch-based Image Retrieval (2017)17.49
• Cross-modal Hierarchical Modelling For Fine-grained Sketch Based Image Retrieval (2020)6.77
• Unsupervised Deep Hashing For Large-scale Visual Search (2016)9.59
• Structured Deep Hashing With Convolutional Neural Networks For Fast Person Re-identification (2017)12.87
• Making Online Sketching Hashing Even Faster (2020)9.23
• Deepsketch: A New Machine Learning-based Reference Search Technique For Post-deduplication Delta Compression (2022)0.00
• SSDH: Semi-supervised Deep Hashing For Large Scale Image Retrieval (2016)15.40