Bag of Tricks and A Strong baseline for Image Copy Detection
arXiv:2111.08004
Abstract
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.
arXiv commentarXiv admin note: substantial text overlap with arXiv:2111.07090
References in corpus (9)
- Bootstrap your own latent: A new approach to self-supervised Learning
- In Defense of the Triplet Loss for Person Re-Identification
- Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
- VehicleNet: Learning Robust Visual Representation for Vehicle Re-identification
- SoftTriple Loss: Deep Metric Learning Without Triplet Sampling
- MultiGrain: a unified image embedding for classes and instances
- DomainMix: Learning Generalizable Person Re-Identification Without Human Annotations
- Momentum^2 Teacher: Momentum Teacher with Momentum Statistics for Self-Supervised Learning
- The 2021 Image Similarity Dataset and Challenge