Domain-Adaptive Self-Supervised Pre-Training for Face & Body Detection in Drawings

TL;DR

This paper introduces a domain-adaptive self-supervised pre-training method for face and body detection in drawings, leveraging unlabeled data and style transfer to achieve state-of-the-art results with minimal annotations.

Contribution

It proposes a novel teacher-student self-supervised learning framework with style transfer integration for detecting faces and bodies in diverse drawing styles.

Findings

Achieves state-of-the-art detection performance with limited labeled data.

Effectively utilizes unlabeled target domain data for training.

Incorporates style transfer to leverage out-of-domain labeled images.

Abstract

Drawings are powerful means of pictorial abstraction and communication. Understanding diverse forms of drawings, including digital arts, cartoons, and comics, has been a major problem of interest for the computer vision and computer graphics communities. Although there are large amounts of digitized drawings from comic books and cartoons, they contain vast stylistic variations, which necessitate expensive manual labeling for training domain-specific recognizers. In this work, we show how self-supervised learning, based on a teacher-student network with a modified student network update design, can be used to build face and body detectors. Our setup allows exploiting large amounts of unlabeled data from the target domain when labels are provided for only a small subset of it. We further demonstrate that style transfer can be incorporated into our learning pipeline to bootstrap detectors using a vast amount of out-of-domain labeled images from natural images (i.e., images from the real world). Our combined architecture yields detectors with state-of-the-art (SOTA) and near-SOTA performance using minimal annotation effort. Our code can be accessed from https://github.com/barisbatuhan/DASS_Detector.