1st Place Solution in Google Universal Images Embedding
This is an incremental improvement for image embedding tasks in competitions, specifically addressing the Kaggle challenge.
The paper tackled the Google Universal Images Embedding Competition by developing a solution that achieved first place with a score of 0.728 on the private leaderboard, focusing on novel training methods and ensemble strategies.
This paper presents the 1st place solution for the Google Universal Images Embedding Competition on Kaggle. The highlighted part of our solution is based on 1) A novel way to conduct training and fine-tuning; 2) The idea of a better ensemble in the pool of models that make embedding; 3) The potential trade-off between fine-tuning on high-resolution and overlapping patches; 4) The potential factors to work for the dynamic margin. Our solution reaches 0.728 in the private leader board, which achieve 1st place in Google Universal Images Embedding Competition.