Do Generalised Classifiers really work on Human Drawn Sketches?

TL;DR

This paper introduces a novel approach that adapts CLIP for human sketch understanding, enabling better generalisation across categories and abstraction levels, surpassing existing methods in zero-shot and few-shot scenarios.

Contribution

It proposes a sketch-aware CLIP model with sketch-specific prompts and a codebook of abstraction prompts, advancing generalised sketch classification across unknown categories and abstraction levels.

Findings

Outperforms existing sketch representation methods in zero-shot learning

Effective across different abstraction levels from edge-maps to doodles

Surpasses prior algorithms in few-shot learning scenarios

Abstract

This paper, for the first time, marries large foundation models with human sketch understanding. We demonstrate what this brings -- a paradigm shift in terms of generalised sketch representation learning (e.g., classification). This generalisation happens on two fronts: (i) generalisation across unknown categories (i.e., open-set), and (ii) generalisation traversing abstraction levels (i.e., good and bad sketches), both being timely challenges that remain unsolved in the sketch literature. Our design is intuitive and centred around transferring the already stellar generalisation ability of CLIP to benefit generalised learning for sketches. We first "condition" the vanilla CLIP model by learning sketch-specific prompts using a novel auxiliary head of raster to vector sketch conversion. This importantly makes CLIP "sketch-aware". We then make CLIP acute to the inherently different sketch abstraction levels. This is achieved by learning a codebook of abstraction-specific prompt biases, a weighted combination of which facilitates the representation of sketches across abstraction levels -- low abstract edge-maps, medium abstract sketches in TU-Berlin, and highly abstract doodles in QuickDraw. Our framework surpasses popular sketch representation learning algorithms in both zero-shot and few-shot setups and in novel settings across different abstraction boundaries.