Efficient And Discriminative Image Feature Extraction For Universal Image Retrieval

Abstract

Current image retrieval systems often face domain specificity and generalization issues. This study aims to overcome these limitations by developing a computationally efficient training framework for a universal feature extractor that provides strong semantic image representations across various domains. To this end, we curated a multi-domain training dataset, called M4D-35k, which allows for resource-efficient training. Additionally, we conduct an extensive evaluation and comparison of various state-of-the-art visual-semantic foundation models and margin-based metric learning loss functions regarding their suitability for efficient universal feature extraction. Despite constrained computational resources, we achieve near state-of-the-art results on the Google Universal Image Embedding Challenge, with a mMP@5 of 0.721. This places our method at the second rank on the leaderboard, just 0.7 percentage points behind the best performing method. However, our model has 32% fewer overall para

Stats

• citations1
• S2 citations—
• github stars21
• HF likes0
• heat score4.94
• arxiv keyflorek2024efficient

Related papers

• Unicom: Universal And Compact Representation Learning For Image Retrieval (2023)5.70
• Test-time Training For Data-efficient UCDR (2022)0.00
• Unifying Deep Local And Global Features For Image Search (2020)28.10
• General Image Descriptors For Open World Image Retrieval Using Vit CLIP (2022)0.00
• Semantic Feature Learning For Universal Unsupervised Cross-domain Retrieval (2024)0.00
• FORB: A Flat Object Retrieval Benchmark For Universal Image Embedding (2023)2.23
• Feature Representation Learning For Unsupervised Cross-domain Image Retrieval (2022)11.46
• Unifying Specialist Image Embedding Into Universal Image Embedding (2020)0.00