A Benchmark on Tricks for Large-scale Image Retrieval

Abstract

Many studies have been performed on metric learning, which has become a key ingredient in top-performing methods of instance-level image retrieval. Meanwhile, less attention has been paid to pre-processing and post-processing tricks that can significantly boost performance. Furthermore, we found that most previous studies used small scale datasets to simplify processing. Because the behavior of a feature representation in a deep learning model depends on both domain and data, it is important to understand how model behave in large-scale environments when a proper combination of retrieval tricks is used. In this paper, we extensively analyze the effect of well-known pre-processing, post-processing tricks, and their combination for large-scale image retrieval. We found that proper use of these tricks can significantly improve model performance without necessitating complex architecture or introducing loss, as confirmed by achieving a competitive result on the Google Landmark Retrieval Challenge 2019.

References in corpus (9)

• Scikit-learn: Machine Learning in Python
• Bag of Tricks for Image Classification with Convolutional Neural Networks
• Combination of Multiple Global Descriptors for Image Retrieval
• MultiGrain: a unified image embedding for classes and instances
• Batch DropBlock Network for Person Re-identification and Beyond
• Semi-supervised Feature-Level Attribute Manipulation for Fashion Image Retrieval
• Semi-Supervised Segmentation of Salt Bodies in Seismic Images using an Ensemble of Convolutional Neural Networks
• Detect-to-Retrieve: Efficient Regional Aggregation for Image Search
• Efficient Image Retrieval via Decoupling Diffusion into Online and Offline Processing