对比FAISS与Annoy在图像检索中的表现，优化特征提取与索引的配合。
Optimizing Domain-Specific Image Retrieval: A Benchmark of FAISS and Annoy with Fine-Tuned Features
- 用微调的ResNet50结合FAISS和Annoy进行近似最近邻搜索。
- FAISS-PQ达98.40%精度，索引仅0.24MB；Annoy查询快至0.00015秒。
- 适合构建高效图像检索系统的研究者与工程师参考。
近似最近邻搜索是高规模数据检索性能的关键。本研究通过微调ResNet50模型，将特征提取与多种ANN方法（FAISS与Annoy）相结合，在自建图像数据集上评估了索引时间、内存占用、查询时间、精确率、召回率、F1分数及Recall@5。结果显示，FAISS的乘积量化（Product Quantization）在仅0.24MB索引大小下实现98.40%的精确率，而Annoy查询速度最快，平均耗时0.00015秒，略有精度损失。这些结果揭示了速度、准确率与内存效率间的权衡，为基于特征的图像检索系统优化提供了可操作的指导，可作为实际检索流水线构建的蓝图。
原文摘要 · Abstract (English)
Approximate Nearest Neighbor search is one of the keys to high-scale data retrieval performance in many applications. The work is a bridge between feature extraction and ANN indexing through fine-tuning a ResNet50 model with various ANN methods: FAISS and Annoy. We evaluate the systems with respect to indexing time, memory usage, query time, precision, recall, F1-score, and Recall@5 on a custom image dataset. FAISS's Product Quantization can achieve a precision of 98.40% with low memory usage at 0.24 MB index size, and Annoy is the fastest, with average query times of 0.00015 seconds, at a slight cost to accuracy. These results reveal trade-offs among speed, accuracy, and memory efficiency and offer actionable insights into the optimization of feature-based image retrieval systems. This study will serve as a blueprint for constructing actual retrieval pipelines and be built on fine-tuned deep learning networks and associated ANN methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。