DeepAI AI Chat
Log In Sign Up

Graph Jigsaw Learning for Cartoon Face Recognition

by   Yong Li, et al.
Nanjing University
Institute of Computing Technology, Chinese Academy of Sciences

Cartoon face recognition is challenging as they typically have smooth color regions and emphasized edges, the key to recognize cartoon faces is to precisely perceive their sparse and critical shape patterns. However, it is quite difficult to learn a shape-oriented representation for cartoon face recognition with convolutional neural networks (CNNs). To mitigate this issue, we propose the GraphJigsaw that constructs jigsaw puzzles at various stages in the classification network and solves the puzzles with the graph convolutional network (GCN) in a progressive manner. Solving the puzzles requires the model to spot the shape patterns of the cartoon faces as the texture information is quite limited. The key idea of GraphJigsaw is constructing a jigsaw puzzle by randomly shuffling the intermediate convolutional feature maps in the spatial dimension and exploiting the GCN to reason and recover the correct layout of the jigsaw fragments in a self-supervised manner. The proposed GraphJigsaw avoids training the classification model with the deconstructed images that would introduce noisy patterns and are harmful for the final classification. Specially, GraphJigsaw can be incorporated at various stages in a top-down manner within the classification model, which facilitates propagating the learned shape patterns gradually. GraphJigsaw does not rely on any extra manual annotation during the training process and incorporates no extra computation burden at inference time. Both quantitative and qualitative experimental results have verified the feasibility of our proposed GraphJigsaw, which consistently outperforms other face recognition or jigsaw-based methods on two popular cartoon face datasets with considerable improvements.


page 1

page 2

page 9

page 10

page 12


Face-GCN: A Graph Convolutional Network for 3D Dynamic Face Identification/Recognition

Face identification/recognition has significantly advanced over the past...

Shape Primitive Histogram: A Novel Low-Level Face Representation for Face Recognition

We further exploit the representational power of Haar wavelet and presen...

Boosting Deep Face Recognition via Disentangling Appearance and Geometry

In this paper, we propose a framework for disentangling the appearance a...

Hierarchical Deep CNN Feature Set-Based Representation Learning for Robust Cross-Resolution Face Recognition

Cross-resolution face recognition (CRFR), which is important in intellig...

Machines Learn Appearance Bias in Face Recognition

We seek to determine whether state-of-the-art, black box face recognitio...

On Matching Faces with Alterations due to Plastic Surgery and Disguise

Plastic surgery and disguise variations are two of the most challenging ...

Ada-NETS: Face Clustering via Adaptive Neighbour Discovery in the Structure Space

Face clustering has attracted rising research interest recently to take ...