Cost-Sensitive Deep Metric Learning for Fine-Grained Image Classification

2018 ◽  
pp. 130-141 ◽  
Author(s):  
Junjie Zhao ◽  
Yuxin Peng
Keyword(s):  
Image Classification ◽  
Metric Learning ◽  
Fine Grained ◽  
Deep Metric Learning

scholarly journals Deep Metric Learning for Cervical Image Classification

IEEE Access ◽  
2021 ◽  
Vol 9 ◽  
pp. 53266-53275
Author(s):  
Anabik Pal ◽  
Zhiyun Xue ◽  
Brian Befano ◽  
Ana Cecilia Rodriguez ◽  
L. Rodney Long ◽  
...  
Keyword(s):  
Image Classification ◽  
Metric Learning ◽  
Deep Metric Learning

N-Cluster Loss and Hard Sample Generative Deep Metric Learning for PolSAR Image Classification

2021 ◽  
pp. 1-16
Author(s):  
Chen Yang ◽  
Biao Hou ◽  
Jocelyn Chanussot ◽  
Yue Hu ◽  
Bo Ren ◽  
...  
Keyword(s):  
Image Classification ◽  
Metric Learning ◽  
Deep Metric Learning

scholarly journals Deep Metric Learning by Online Soft Mining and Class-Aware Attention

2019 ◽  
Vol 33 ◽  
pp. 5361-5368 ◽  
Author(s):  
Xinshao Wang ◽  
Yang Hua ◽  
Elyor Kodirov ◽  
Guosheng Hu ◽  
Neil M. Robertson
Keyword(s):  
Large Fraction ◽  
Metric Learning ◽  
Improve Performance ◽  
Fine Grained ◽  
Training Samples ◽  
Deep Embedding ◽  
Data Points ◽  
Accelerate Convergence ◽  
Deep Metric Learning ◽  
Mining Methods

Deep metric learning aims to learn a deep embedding that can capture the semantic similarity of data points. Given the availability of massive training samples, deep metric learning is known to suffer from slow convergence due to a large fraction of trivial samples. Therefore, most existing methods generally resort to sample mining strategies for selecting nontrivial samples to accelerate convergence and improve performance. In this work, we identify two critical limitations of the sample mining methods, and provide solutions for both of them. First, previous mining methods assign one binary score to each sample, i.e., dropping or keeping it, so they only selects a subset of relevant samples in a mini-batch. Therefore, we propose a novel sample mining method, called Online Soft Mining (OSM), which assigns one continuous score to each sample to make use of all samples in the mini-batch. OSM learns extended manifolds that preserve useful intraclass variances by focusing on more similar positives. Second, the existing methods are easily influenced by outliers as they are generally included in the mined subset. To address this, we introduce Class-Aware Attention (CAA) that assigns little attention to abnormal data samples. Furthermore, by combining OSM and CAA, we propose a novel weighted contrastive loss to learn discriminative embeddings. Extensive experiments on two fine-grained visual categorisation datasets and two video-based person re-identification benchmarks show that our method significantly outperforms the state-of-the-art.

scholarly journals Reconstruction Regularized Deep Metric Learning for Multi-Label Image Classification

2019 ◽  
pp. 1-10 ◽  
Author(s):  
Changsheng Li ◽  
Chong Liu ◽  
Lixin Duan ◽  
Peng Gao ◽  
Kai Zheng
Keyword(s):  
Image Classification ◽  
Metric Learning ◽  
Deep Metric Learning
Sign in / Sign up

Export Citation Format

Share Document