arXiv:2010.05350
공식 코드 · Papers with Code
Google Landmark Recognition 2020 Competition Third Place Solution
원문 초록
We present our third place solution to the Google Landmark Recognition 2020 competition. It is an ensemble of global features only Sub-center ArcFace models. We introduce dynamic margins for ArcFace loss, a family of tune-able margin functions of class size, designed to deal with the extreme imbalance in GLDv2 dataset. Progressive finetuning and careful postprocessing are also key to the solution. Our two submissions scored 0.6344 and 0.6289 on private leaderboard, both ranking third place out of 736 teams.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
A Study on Self-Supervised Pretraining for Vision Problems in Gastrointestinal Endoscopy
Efficient large-scale image retrieval with deep feature orthogonality and Hybrid-Swin-Transformers
Supporting large-scale image recognition with out-of-domain samples
Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrieval
Two-stage Discriminative Re-ranking for Large-scale Landmark Retrieval
2nd Place and 2nd Place Solution to Kaggle Landmark Recognition andRetrieval Competition 2019
토론
이 논문과 연결된 포럼 글이 아직 없습니다.