当前位置:
X-MOL 学术
›
Opt. Mem. Neural Networks
›
论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Method for Whale Re-identification Based on Siamese Nets and Adversarial Training
Optical Memory and Neural Networks Pub Date : 2020-07-07 , DOI: 10.3103/s1060992x20020058 W. Wang , R. A. Solovyev , A. L. Stempkovsky , D. V. Telpukhov , A. A. Volkov
中文翻译:
连体网和对抗训练的鲸鱼重新识别方法
更新日期:2020-07-07
Optical Memory and Neural Networks Pub Date : 2020-07-07 , DOI: 10.3103/s1060992x20020058 W. Wang , R. A. Solovyev , A. L. Stempkovsky , D. V. Telpukhov , A. A. Volkov
Abstract
Training Convolutional Neural Networks that do well in one-shot learning settings can have wide range of impacts on real-world datasets. In this paper, we explore an adversarial training method that learns a Siamese neural network in an end-to-end fashion for two models—ConvNets model that learns image embeddings from input image pair, and head model that further learns the distance between those embeddings. We further present an adversarial mining approach that efficiently identifies and selects harder examples during training, which significantly boosts the model performance over difficult cases. We have done a comprehensive evaluation using a public whale identification dataset hosted on Kaggle platform, and report state-of-the-art performance benchmarking against result of other 2000 participants.中文翻译:
连体网和对抗训练的鲸鱼重新识别方法