Weakly Supervised Object Localization with Background Suppression Erasing for Art Authentication and Copyright Protection

• Published in: International journal of automation and computing 2024-02, Vol.21 (1), p.89-103
• Main Authors: Wu, Chaojie, Li, Mingyang, Gao, Ying, Xie, Xinyan, Ng, Wing W. Y., Musyafa, Ahmad
• Format: Article
• Language: English
• Subjects: Annotations; Artificial neural networks; Authentication; Copy protection; Copyright; Localization; Object recognition
• ISSN: 2731-538X; 1476-8186; 2731-5398; 1751-8520
• DOI: 10.1007/s11633-023-1455-3

The problem of art forgery and infringement is becoming increasingly prominent, since diverse self-media contents with all kinds of art pieces are released on the Internet every day. For art paintings, object detection and localization provide an efficient and effective means of art authentication and copyright protection. However, the acquisition of a precise detector requires large amounts of expensive pixel-level annotations. To alleviate this, we propose a novel weakly supervised object localization (WSOL) with background superposition erasing (BSE), which recognizes objects with inexpensive image-level labels. First, integrated adversarial erasing (IAE) for vanilla convolutional neural network (CNN) dropouts the most discriminative region by leveraging high-level semantic information. Second, a background suppression module (BSM) limits the activation area of the IAE to the object region through a self-guidance mechanism. Finally, in the inference phase, we utilize the refined importance map (RIM) of middle features to obtain class-agnostic localization results. Extensive experiments are conducted on paintings, CUB-200-2011 and ILSVRC to validate the effectiveness of our BSE.