On Learning Semantic Representations For Million-scale Free-hand Sketches

Abstract

In this paper, we study learning semantic representations for million-scale free-hand sketches. This is highly challenging due to the domain-unique traits of sketches, e.g., diverse, sparse, abstract, noisy. We propose a dual-branch CNNRNN network architecture to represent sketches, which simultaneously encodes both the static and temporal patterns of sketch strokes. Based on this architecture, we further explore learning the sketch-oriented semantic representations in two challenging yet practical settings, i.e., hashing retrieval and zero-shot recognition on million-scale sketches. Specifically, we use our dual-branch architecture as a universal representation framework to design two sketch-specific deep models: (i) We propose a deep hashing model for sketch retrieval, where a novel hashing loss is specifically designed to accommodate both the abstract and messy traits of sketches. (ii) We propose a deep embedding model for sketch zero-shot recognition, via collecting a large-scale e

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyxu2020on

Related papers

• Deep Self-supervised Representation Learning For Free-hand Sketch (2020)12.25
• Sketchmate: Deep Hashing For Million-scale Human Sketch Retrieval (2018)15.03
• Sketch-bert: Learning Sketch Bidirectional Encoder Representation From Transformers By Self-supervised Learning Of Sketch Gestalt (2020)13.05
• Learning Deep Sketch Abstraction (2018)14.31
• Deep Sketch Hashing: Fast Free-hand Sketch-based Image Retrieval (2017)17.49
• Sketch Down The Flops: Towards Efficient Networks For Human Sketch (2025)0.00
• Back To The Drawing Board: Rethinking Scene-level Sketch-based Image Retrieval (2025)0.00
• Stacked Semantic-guided Network For Zero-shot Sketch-based Image Retrieval (2019)0.00