Classification is a Strong Baseline for Deep Metric Learning

30 Nov 2018  ·  Andrew Zhai, Hao-Yu Wu ·

Deep metric learning aims to learn a function mapping image pixels to embedding feature vectors that model the similarity between images. Two major applications of metric learning are content-based image retrieval and face verification. For the retrieval tasks, the majority of current state-of-the-art (SOTA) approaches are triplet-based non-parametric training. For the face verification tasks, however, recent SOTA approaches have adopted classification-based parametric training. In this paper, we look into the effectiveness of classification based approaches on image retrieval datasets. We evaluate on several standard retrieval datasets such as CAR-196, CUB-200-2011, Stanford Online Product, and In-Shop datasets for image retrieval and clustering, and establish that our classification-based approach is competitive across different feature dimensions and base feature networks. We further provide insights into the performance effects of subsampling classes for scalable classification-based training, and the effects of binarization, enabling efficient storage and computation for practical applications.

PDF Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Image Retrieval CARS196 NormSoftmax2048 (ResNet-50) R@1 89.3 # 3
Image Retrieval CUB-200-2011 NormSoftmax2048 (ResNet-50) R@1 65.3 # 6
Image Retrieval In-Shop NormSoftmax2048 (ResNet-50) R@1 89.4 # 5
Image Retrieval SOP NormSoftmax2048 (ResNet-50) R@1 79.5 # 8