3rd Place: A Global And Local Dual Retrieval Solution To Facebook AI Image Similarity Challenge

Abstract

As a basic task of computer vision, image similarity retrieval is facing the challenge of large-scale data and image copy attacks. This paper presents our 3rd place solution to the matching track of Image Similarity Challenge (ISC) 2021 organized by Facebook AI. We propose a multi-branch retrieval method of combining global descriptors and local descriptors to cover all attack cases. Specifically, we attempt many strategies to optimize global descriptors, including abundant data augmentations, self-supervised learning with a single Transformer model, overlay detection preprocessing. Moreover, we introduce the robust SIFT feature and GPU Faiss for local retrieval which makes up for the shortcomings of the global retrieval. Finally, KNN-matching algorithm is used to judge the match and merge scores. We show some ablation experiments of our method, which reveals the complementary advantages of global and local features.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keysun20213rd

Related papers

• 2nd Place Solution To Facebook AI Image Similarity Challenge Matching Track (2021)0.00
• 3rd Place Solution To "google Landmark Retrieval 2020" (2020)0.00
• Google Landmark Retrieval 2021 Competition Third Place Solution (2021)0.00
• Deep Image Retrieval: Learning Global Representations For Image Search (2016)19.67
• Unifying Deep Local And Global Features For Image Search (2020)28.10
• Semi-supervised Exploration In Image Retrieval (2019)0.00
• 2nd Place Solution To Google Landmark Retrieval 2020 (2022)0.00
• DALG: Deep Attentive Local And Global Modeling For Image Retrieval (2022)0.00