Bag of Tricks and A Strong baseline for Image Copy Detection
This work addresses image copy detection for social media applications, presenting an incremental improvement over existing methods.
The paper tackles image copy detection by proposing a bag of tricks and a strong baseline, replacing supervised pre-training with unsupervised pre-training and introducing a descriptor stretching strategy to stabilize scores. The method ranks third out of 526 participants on the Facebook AI Image Similarity Challenge: Descriptor Track.
Image copy detection is of great importance in real-life social media. In this paper, a bag of tricks and a strong baseline are proposed for image copy detection. Unsupervised pre-training substitutes the commonly-used supervised one. Beyond that, we design a descriptor stretching strategy to stabilize the scores of different queries. Experiments demonstrate that the proposed method is effective. The proposed baseline ranks third out of 526 participants on the Facebook AI Image Similarity Challenge: Descriptor Track. The code and trained models are available at https://github.com/WangWenhao0716/ISC-Track2-Submission.