On Background Bias In Deep Metric Learning

Abstract

Deep Metric Learning trains a neural network to map input images to a lower-dimensional embedding space such that similar images are closer together than dissimilar images. When used for item retrieval, a query image is embedded using the trained model and the closest items from a database storing their respective embeddings are returned as the most similar items for the query. Especially in product retrieval, where a user searches for a certain product by taking a photo of it, the image background is usually not important and thus should not influence the embedding process. Ideally, the retrieval process always returns fitting items for the photographed object, regardless of the environment the photo was taken in. In this paper, we analyze the influence of the image background on Deep Metric Learning models by utilizing five common loss functions and three common datasets. We find that Deep Metric Learning networks are prone to so-called background bias, which can lead to a severe dec

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keykobs2022on

Related papers

• Three Things To Know About Deep Metric Learning (2024)0.00
• Deep Metric Learning For Computer Vision: A Brief Overview (2023)6.77
• Classification Is A Strong Baseline For Deep Metric Learning (2018)0.00
• Unbiased Evaluation Of Deep Metric Learning Algorithms (2019)0.00
• The Group Loss For Deep Metric Learning (2019)11.39
• Shadow Loss: Memory-linear Deep Metric Learning For Efficient Training (2023)0.00
• Dynamic Sampling For Deep Metric Learning (2020)5.84
• Attention-based Ensemble For Deep Metric Learning (2018)15.90