no code implementations • 27 Nov 2019 • Xin-Yu Zhang, Le Zhang, Zao-Yi Zheng, Yun Liu, Jia-Wang Bian, Ming-Ming Cheng
The effectiveness of the triplet loss heavily relies on the triplet selection, in which a common practice is to first sample intra-class patches (positives) from the dataset for batch construction and then mine in-batch negatives to form triplets.