A Benchmark on Tricks for Large-scale Image Retrieval
This work addresses the need for efficient performance boosts in image retrieval for researchers and practitioners, but it is incremental as it focuses on combining existing tricks rather than introducing new methods.
The paper tackles the problem of large-scale image retrieval by analyzing the impact of pre-processing and post-processing tricks, finding that their proper use significantly improves performance without complex architectures, as demonstrated by achieving a competitive result in the Google Landmark Retrieval Challenge 2019.
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.