AMES: Asymmetric And Memory-efficient Similarity Estimation For Instance-level Retrieval

Abstract

This work investigates the problem of instance-level image retrieval re-ranking with the constraint of memory efficiency, ultimately aiming to limit memory usage to 1KB per image. Departing from the prevalent focus on performance enhancements, this work prioritizes the crucial trade-off between performance and memory requirements. The proposed model uses a transformer-based architecture designed to estimate image-to-image similarity by capturing interactions within and across images based on their local descriptors. A distinctive property of the model is the capability for asymmetric similarity estimation. Database images are represented with a smaller number of descriptors compared to query images, enabling performance improvements without increasing memory consumption. To ensure adaptability across different applications, a universal model is introduced that adjusts to a varying number of local descriptors during the testing phase. Results on standard benchmarks demonstrate the super

Stats

• citations6
• S2 citations—
• github stars47
• HF likes0
• heat score9.70
• arxiv keysuma2024ames

Related papers

• Connecting Images Through Time And Sources: Introducing Low-data, Heterogeneous Instance Retrieval (2021)0.00
• Efficient Bitmap-based Indexing And Retrieval Of Similarity Search Image Queries (2019)0.00
• Optimizing Top Precision Performance Measure Of Content-based Image Retrieval By Learning Similarity Function (2016)9.59
• Ascent Similarity Caching With Approximate Indexes (2021)2.26
• Patch-wise Retrieval: A Bag Of Practical Techniques For Instance-level Matching (2025)0.00
• On The Unreasonable Effectiveness Of Centroids In Image Retrieval (2021)14.80
• STIR: Siamese Transformer For Image Retrieval Postprocessing (2023)11.23
• Exploiting Local Indexing And Deep Feature Confidence Scores For Fast Image-to-video Search (2018)2.26