On Learning Density Aware Embeddings

Soumyadeep Ghosh, Richa Singh, Mayank Vatsa
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
Deep metric learning algorithms have been utilized to learn discriminative and generalizable models which are effective for classifying unseen classes. In this paper, a novel noise tolerant deep metric learning algorithm is proposed. The proposed method, termed as Density Aware Metric Learning, enforces the model to learn embeddings that are pulled towards the most dense region of the clusters for each class. It is achieved by iteratively shifting the estimate of the center towards the dense
more » ... ion of the cluster thereby leading to faster convergence and higher generalizability. In addition to this, the approach is robust to noisy samples in the training data, often present as outliers. Detailed experiments and analysis on two challenging cross-modal face recognition databases and two popular object recognition databases exhibit the efficacy of the proposed approach. It has superior convergence, requires lesser training time, and yields better accuracies than several popular deep metric learning methods.
doi:10.1109/cvpr.2019.00502 dblp:conf/cvpr/Ghosh0V19 fatcat:azpqszdysbdtrkvpaxmq75qbhq