Adversarial Training For Sketch Retrieval

Abstract

Generative Adversarial Networks (GAN) are able to learn excellent representations for unlabelled data which can be applied to image generation and scene classification. Representations learned by GANs have not yet been applied to retrieval. In this paper, we show that the representations learned by GANs can indeed be used for retrieval. We consider heritage documents that contain unlabelled Merchant Marks, sketch-like symbols that are similar to hieroglyphs. We introduce a novel GAN architecture with design features that make it suitable for sketch retrieval. The performance of this sketch-GAN is compared to a modified version of the original GAN architecture with respect to simple invariance properties. Experiments suggest that sketch-GANs learn representations that are suitable for retrieval and which also have increased stability to rotation, scale and translation compared to the standard GAN architecture.

Stats

• citations30
• S2 citations—
• github stars0
• HF likes0
• heat score11.19
• arxiv keycreswell2016adversarial

Related papers

• Generative Model For Zero-shot Sketch-based Image Retrieval (2019)9.23
• Back To The Drawing Board: Rethinking Scene-level Sketch-based Image Retrieval (2025)0.00
• Stacked Adversarial Network For Zero-shot Sketch Based Image Retrieval (2020)10.74
• How To Handle Sketch-abstraction In Sketch-based Image Retrieval? (2024)10.48
• Unsupervised Adversarial Attacks On Deep Feature-based Retrieval With GAN (2019)0.00
• Sketching Without Worrying: Noise-tolerant Sketch-based Image Retrieval (2022)12.74
• Adaptive Fine-grained Sketch-based Image Retrieval (2022)9.76
• Sketch Less For More: On-the-fly Fine-grained Sketch Based Image Retrieval (2020)15.28