paper-with-me

홈 › Papers

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 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.

📄 PDF Abstract BibTeX arXiv:2210.08473

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

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 …

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 …

2nd Place Solution to Google Universal Image Embedding

2022-10-17 · Xiaolong Huang, Qiankun Li

Image representations are a critical building block of computer vision applications. This paper presents the 2nd place solution to the Google Universal Image Embedding Competition, which is part of the ECCV2022 instance-…

Fine-Grained Image Classificationimage-classificationImage Classification

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

3rd Place Solution to Google Landmark Recognition Competition 2021

2021-10-06 · Cheng Xu, Weimin WANG, Shuai Liu, Yong Wang 외

In this paper, we show our solution to the Google Landmark Recognition 2021 Competition. Firstly, embeddings of images are extracted via various architectures (i.e. CNN-, Transformer- and hybrid-based), which are optimiz…

Landmark RecognitionRetrieval