Divide and Conquer the Embedding Space for Metric Learning

by   Artsiom Sanakoyeu, et al.

Learning the embedding space, where semantically similar objects are located close together and dissimilar objects far apart, is a cornerstone of many computer vision applications. Existing approaches usually learn a single metric in the embedding space for all available data points, which may have a very complex non-uniform distribution with different notions of similarity between objects, e.g. appearance, shape, color or semantic meaning. Approaches for learning a single distance metric often struggle to encode all different types of relationships and do not generalize well. In this work, we propose a novel easy-to-implement divide and conquer approach for deep metric learning, which significantly improves the state-of-the-art performance of metric learning. Our approach utilizes the embedding space more efficiently by jointly splitting the embedding space and data into K smaller sub-problems. It divides both, the data and the embedding space into K subsets and learns K separate distance metrics in the non-overlapping subspaces of the embedding space, defined by groups of neurons in the embedding layer of the neural network. The proposed approach increases the convergence speed and improves generalization since the complexity of each sub-problem is reduced compared to the original one. We show that our approach outperforms the state-of-the-art by a large margin in retrieval, clustering and re-identification tasks on CUB200-2011, CARS196, Stanford Online Products, In-shop Clothes and PKU VehicleID datasets.


page 2

page 3

page 4

page 12


Improving Deep Metric Learning by Divide and Conquer

Deep metric learning (DML) is a cornerstone of many computer vision appl...

Deep Metric Learning via Facility Location

Learning the representation and the similarity metric in an end-to-end f...

Learning to embed semantic similarity for joint image-text retrieval

We present a deep learning approach for learning the joint semantic embe...

DAS: Densely-Anchored Sampling for Deep Metric Learning

Deep Metric Learning (DML) serves to learn an embedding function to proj...

Transferable Deep Metric Learning for Clustering

Clustering in high dimension spaces is a difficult task; the usual dista...

Human Motion Analysis with Deep Metric Learning

Effectively measuring the similarity between two human motions is necess...

Caging Loops in Shape Embedding Space: Theory and Computation

We propose to synthesize feasible caging grasps for a target object thro...

Please sign up or login with your details

Forgot password? Click here to reset