5th Place Solution to Kaggle Google Universal Image Embedding Competition

2022-10-18 · Noriaki Ota, Shingo Yokoi, Shinsuke Yamaoka

In this paper, we present our solution, which placed 5th in the kaggle Google Universal Image Embedding Competition in 2022. We use the ViT-H visual encoder of CLIP from the openclip repository as a backbone and train a head model composed of BatchNormalization and Linear layers using ArcFace. The dataset used was a subset of products10K, GLDv2, GPR1200, and Food101. And applying TTA for part of images also improves the score. With this method, we achieve a score of 0.684 on the public and 0.688 on the private leaderboard. Our code is available. https://github.com/riron1206/kaggle-Google-Universal-Image-Embedding-Competition-5th-Place-Solution

📄 PDF Abstract BibTeX arXiv:2210.09495

Code (1)

riron1206/kaggle-google-universal-image-embedding-competition-5th-place-solution 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…

ArcFace ArcFace, or Additive Angular Margin Loss, is a loss function used in face recognition tasks. The softmax is traditionally used…

3rd Place Solution for Google Universal Image Embedding

2022-10-14 · Nobuaki Aoki, Yasumasa Namba

This paper presents the 3rd place solution to the Google Universal Image Embedding Competition on Kaggle. We use ViT-H/14 from OpenCLIP for the backbone of ArcFace, and trained in 2 stage. 1st stage is done with freezed …

1st Place Solution in Google Universal Images Embedding

2022-10-16 · Shihao Shao, Qinghua Cui

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…

6th Place Solution to Google Universal Image Embedding

2022-10-17 · S. Gkelios, A. Kastellos, S. Chatzichristofis

This paper presents the 6th place solution to the Google Universal Image Embedding competition on Kaggle. Our approach is based on the CLIP architecture, a powerful pre-trained model used to learn visual representation f…

Transfer Learning

2nd Place Solution to Google Landmark Retrieval 2021

2021-10-08 · Zhang Yuqi, Xu Xianzhe, Chen Weihua, Wang Yaohua 외

This paper presents the 2nd place solution to the Google Landmark Retrieval 2021 Competition on Kaggle. The solution is based on a baseline with training tricks from person re-identification, a continent-aware sampling s…

Image Retrieval Person Re-Identification Reranking Retrieval

1st Place Solution to Google Landmark Retrieval 2020

2020-08-24 · SeungKee Jeon

This paper presents the 1st place solution to the Google Landmark Retrieval 2020 Competition on Kaggle. The solution is based on metric learning to classify numerous landmark classes, and uses transfer learning with two …

Metric Learning Retrieval Transfer Learning