Classification is a Strong Baseline for Deep Metric Learning

Abstract

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.

arXiv commentAccepted to BMVC 2019

References in corpus (7)

• Caffe: Convolutional Architecture for Fast Feature Embedding
• Going Deeper with Convolutions
• Learning Deep Embeddings with Histogram Loss
• No Fuss Distance Metric Learning using Proxies
• Visual Discovery at Pinterest
• Improving Generalization via Scalable Neighborhood Component Analysis
• Hard-Aware Deeply Cascaded Embedding

Cited by in corpus (10)

• Training Vision Transformers for Image Retrieval
• Enriched Music Representations with Multiple Cross-modal Contrastive Learning
• Temperature check: theory and practice for training models with softmax-cross-entropy losses
• It Takes Two to Tango: Mixup for Deep Metric Learning
• BroadFace: Looking at Tens of Thousands of People at Once for Face Recognition
• Ranked List Loss for Deep Metric Learning
• Uniform Priors for Data-Efficient Transfer
• CAMRI Loss: Improving Recall of a Specific Class without Sacrificing Accuracy
• Learning a Unified Embedding for Visual Search at Pinterest
• Dynamic Metric Learning: Towards a Scalable Metric Space to Accommodate Multiple Semantic Scales