Efficient large-scale image retrieval with deep feature orthogonality and Hybrid-Swin-Transformers
arXiv:2110.03786
Abstract
We present an efficient end-to-end pipeline for largescale landmark recognition and retrieval. We show how to combine and enhance concepts from recent research in image retrieval and introduce two architectures especially suited for large-scale landmark identification. A model with deep orthogonal fusion of local and global features (DOLG) using an EfficientNet backbone as well as a novel Hybrid-Swin-Transformer is discussed and details how to train both architectures efficiently using a step-wise approach and a sub-center arcface loss with dynamic margins are provided. Furthermore, we elaborate a novel discriminative re-ranking methodology for image retrieval. The superiority of our approach was demonstrated by winning the recognition and retrieval track of the Google Landmark Competition 2021.
References in corpus (6)
- WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learning
- Unifying Deep Local and Global Features for Image Search
- Large-scale Landmark Retrieval/Recognition under a Noisy and Diverse Dataset
- Google Landmark Recognition 2020 Competition Third Place Solution
- Supporting large-scale image recognition with out-of-domain samples
- Towards A Fairer Landmark Recognition Dataset