On The Unreasonable Effectiveness Of Centroids In Image Retrieval

Abstract

Image retrieval task consists of finding similar images to a query image from a set of gallery (database) images. Such systems are used in various applications e.g. person re-identification (ReID) or visual product search. Despite active development of retrieval models it still remains a challenging task mainly due to large intra-class variance caused by changes in view angle, lighting, background clutter or occlusion, while inter-class variance may be relatively low. A large portion of current research focuses on creating more robust features and modifying objective functions, usually based on Triplet Loss. Some works experiment with using centroid/proxy representation of a class to alleviate problems with computing speed and hard samples mining used with Triplet Loss. However, these approaches are used for training alone and discarded during the retrieval stage. In this paper we propose to use the mean centroid representation both during training and retrieval. Such an aggregated rep

Stats

• citations93
• S2 citations—
• github stars0
• HF likes0
• heat score14.80
• arxiv keywieczorek2021on

Related papers

• Object-centric Open-vocabulary Image-retrieval With Aggregated Features (2023)0.00
• AMES: Asymmetric And Memory-efficient Similarity Estimation For Instance-level Retrieval (2024)9.70
• Person Re-identification Via Generalized Class Prototypes (2025)0.00
• Improved Deep Classwise Hashing With Centers Similarity Learning For Image Retrieval (2021)5.84
• Central Similarity Quantization For Efficient Image And Video Retrieval (2019)23.49
• Confidence-guided Centroids For Unsupervised Person Re-identification (2022)7.16
• Unicom: Universal And Compact Representation Learning For Image Retrieval (2023)5.70
• Image Retrieval Methods In The Dissimilarity Space (2024)0.00