02/02/2021

Multi-level Distance Regularization for Deep Metric Learning

Yonghyun Kim, Wonpyo Park

Keywords:

Abstract Paper Similar Papers

Abstract: We propose a novel distance-based regularization method for deep metric learning called Multi-level Distance Regularization (MDR). MDR explicitly disturbs a learning procedure by regularizing pairwise distances between embedding vectors into multiple levels that represents a degree of similarity between a pair. In the training stage, the model is trained with both MDR and an existing loss function of deep metric learning, simultaneously; the two losses interfere with the objective of each other, and it makes the learning process difficult. Moreover, MDR prevents some examples from being ignored or overly influenced in the learning process. These allow the parameters of the embedding network to be settle on a local optima with better generalization. Without bells and whistles, MDR with simple Triplet loss achieves the-state-of-the-art performance in various benchmark datasets: CUB-200-2011, Cars-196, Stanford Online Products, and In-Shop Clothes Retrieval. We extensively perform ablation studies on its behaviors to show the effectiveness of MDR. By easily adopting our MDR, the previous approaches can be improved in performance and generalization ability.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38947839
(Link will open in new window)
 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at AAAI 2021 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers

 0
 0
 0
 0
 1:00 
 0
 0
 0
 0
 0:56 
 0
 0
 0
 0
 4:44 
 0
 0
 0
 0
 5:01 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 12:36 
 0
 0
 0
 0
 5:11 
 0
 0
 0
 0
 2:50 
 0
 0
 0
 0
 6:35 
 0
 0
 0
 0
 5:16 
 0
 0
 0
 0
 15:59 
 0
 0
 0
 0
 15:15 
 0
 0
 0
 0
 16:59 
 0
 0
 0
 0
 7:16 
 1
 0
 0
 1
 5:03 
 0
 0
 0
 0
 1:00 
 0
 0
 0
 0
 16:02 
 0
 0
 0
 0
 15:15 
 0
 0
 0
 0
 13:42 
 0
 0
 0
 0
 9:03 
 0
 0
 0
 0
 4:57 
 0
 0
 0
 0
 9:19 
 0
 0
 0
 0
 6:30 
 0
 0
 0
 0
 8:56 
 0
 0
 0
 0
 5:10 
 0
 0
 0
 0
 3:22 
 0
 0
 0
 0
 4:56 
 0
 0
 0
 0
 4:23 
 0
 0
 0
 0
 1:00 
 0
 0
 0
 0
 21:24 
 0
 0
 0
 0
 12:10 
 0
 0
 0
 0
 3:29 
 0
 0
 0
 0
 14:27 
 0
 0
 0
 0
 3:23 
 0
 0
 0
 0
 13:34 
 0
 0
 0
 0
 3:17 
 0
 0
 0
 0
 5:35 
 1
 0
 0
 0
 6:21 
 0
 0
 0
 0
 13:27 
 0
 0
 0
 0
 1:01