# Sketch-a-Classifier: Sketch-based Photo Classifier Generation

arXiv: https://arxiv.org/abs/1804.11182 · HTML: https://mlsanity.com/paper/1804.11182/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Apr 2018.

## Built on by (most cited first, 6 of 6)

- [What Can Human Sketches Do for Object Detection?](https://mlsanity.com/paper/2303.15149/) (2023)
- [Adaptive Fine-Grained Sketch-Based Image Retrieval](https://mlsanity.com/paper/2207.01723/) (2022)
- [SketchINR: A First Look into Sketches as Implicit Neural Representations](https://mlsanity.com/paper/2403.09344/) (2024)
- [Automating Style Analysis and Visualization With Explainable AI -- Case Studies on Brand Recognition](https://mlsanity.com/paper/2306.03021/) (2023)
- [Sketch-based Video Object Segmentation: Benchmark and Analysis](https://mlsanity.com/paper/2311.07261/) (2023)
- [ViSketch-GPT: Collaborative Multi-Scale Feature Extraction for Sketch Recognition and Generation](https://mlsanity.com/paper/2503.22374/) (2025)

## Abstract (arXiv)

Contemporary deep learning techniques have made image recognition a reasonably reliable technology. However training effective photo classifiers typically takes numerous examples which limits image recognition's scalability and applicability to scenarios where images may not be available. This has motivated investigation into zero-shot learning, which addresses the issue via knowledge transfer from other modalities such as text. In this paper we investigate an alternative approach of synthesizing image classifiers: almost directly from a user's imagination, via free-hand sketch. This approach doesn't require the category to be nameable or describable via attributes as per zero-shot learning. We achieve this via training a {model regression} network to map from {free-hand sketch} space to the space of photo classifiers. It turns out that this mapping can be learned in a category-agnostic way, allowing photo classifiers for new categories to be synthesized by user with no need for annotated training photos. {We also demonstrate that this modality of classifier generation can also be used to enhance the granularity of an existing photo classifier, or as a complement to name-based zero-shot learning.