Distribution Context Aware Loss for Person Re-identification

11/17/2019
by   Zhigang Chang, et al.
0

To learn the optimal similarity function between probe and gallery images in Person re-identification, effective deep metric learning methods have been extensively explored to obtain discriminative feature embedding. However, existing metric loss like triplet loss and its variants always emphasize pair-wise relations but ignore the distribution context in feature space, leading to inconsistency and sub-optimal. In fact, the similarity of one pair not only decides the match of this pair, but also has potential impacts on other sample pairs. In this paper, we propose a novel Distribution Context Aware (DCA) loss based on triplet loss to combine both numerical similarity and relation similarity in feature space for better clustering. Extensive experiments on three benchmarks including Market-1501, DukeMTMC-reID and MSMT17, evidence the favorable performance of our method against the corresponding baseline and other state-of-the-art methods.

READ FULL TEXT
research
08/20/2018

Person Re-Identification by Semantic Region Representation and Topology Constraint

Person re-identification is a popular research topic which aims at match...
research
03/27/2018

Dual Attention Matching Network for Context-Aware Feature Sequence based Person Re-Identification

Typical person re-identification (ReID) methods usually describe each pe...
research
12/08/2020

Context-Aware Graph Convolution Network for Target Re-identification

Most existing re-identification methods focus on learning robust and dis...
research
04/24/2018

Homocentric Hypersphere Feature Embedding for Person Re-identification

Person re-identification (Person ReID) is a challenging task due to the ...
research
12/02/2018

Deep Cosine Metric Learning for Person Re-Identification

Metric learning aims to construct an embedding where two extracted featu...
research
02/25/2020

Circle Loss: A Unified Perspective of Pair Similarity Optimization

This paper provides a pair similarity optimization viewpoint on deep fea...
research
04/01/2018

Graph Correspondence Transfer for Person Re-identification

In this paper, we propose a graph correspondence transfer (GCT) approach...

Please sign up or login with your details

Forgot password? Click here to reset