Efficient Large-scale Image Retrieval With Deep Feature Orthogonality And Hybrid-swin-transformers

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.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyhenkel2021efficient

Related papers

• Two-stage Discriminative Re-ranking For Large-scale Landmark Retrieval (2020)15.20
• Large-scale Image Retrieval With Attentive Deep Local Features (2016)30.63
• Semi-supervised Exploration In Image Retrieval (2019)0.00
• Large-scale Landmark Retrieval/recognition Under A Noisy And Diverse Dataset (2019)0.00
• DOLG: Single-stage Image Retrieval With Deep Orthogonal Fusion Of Local And Global Features (2021)15.95
• Deep Image Retrieval: Learning Global Representations For Image Search (2016)19.67
• Content-based Landmark Retrieval Combining Global And Local Features Using Siamese Neural Networks (2022)0.00
• A Benchmark On Tricks For Large-scale Image Retrieval (2019)0.00