Sketch Down The Flops: Towards Efficient Networks For Human Sketch

Abstract

As sketch research has collectively matured over time, its adaptation for at-mass commercialisation emerges on the immediate horizon. Despite an already mature research endeavour for photos, there is no research on the efficient inference specifically designed for sketch data. In this paper, we first demonstrate existing state-of-the-art efficient light-weight models designed for photos do not work on sketches. We then propose two sketch-specific components which work in a plug-n-play manner on any photo efficient network to adapt them to work on sketch data. We specifically chose fine-grained sketch-based image retrieval (FG-SBIR) as a demonstrator as the most recognised sketch problem with immediate commercial value. Technically speaking, we first propose a cross-modal knowledge distillation network to transfer existing photo efficient networks to be compatible with sketch, which brings down number of FLOPs and model parameters by 97.96% percent and 84.89% respectively. We then explo

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keysain2025sketch

Related papers

• Sketch Less For More: On-the-fly Fine-grained Sketch Based Image Retrieval (2020)15.28
• Active Learning For Fine-grained Sketch-based Image Retrieval (2023)0.00
• Deep Factorised Inverse-sketching (2018)8.35
• Cross-modal Hierarchical Modelling For Fine-grained Sketch Based Image Retrieval (2020)6.77
• Sketching Without Worrying: Noise-tolerant Sketch-based Image Retrieval (2022)12.74
• Sketch Less Face Image Retrieval: A New Challenge (2023)6.34
• Exploiting Unlabelled Photos For Stronger Fine-grained SBIR (2023)10.61
• Sketchmate: Deep Hashing For Million-scale Human Sketch Retrieval (2018)15.03