Nov 26, 2019 · This paper develops a novel loss function, which adaptively emphasizes the mis-classified feature vectors to guide the discriminative feature learning.

So increasingly more researchers shift their attention to construct deep face recognition models by re-designing the classical classification loss functions.

SV-X-Softmax is a new loss function, which adaptively emphasizes the mis-classified feature vectors to guide the discriminative feature learning.

This paper develops a novel loss function, which adaptively emphasizes the mis-classified feature vectors to guide the discriminative feature learning and ...

To cope with these issues, this paper develops a novel loss function, which adaptively emphasizes the mis-classified feature vectors to guide the discriminative ...

Dec 29, 2018 · In this paper, we design a novel loss function, namely support vector guided softmax loss (SV-Softmax), which adaptively emphasizes the mis-classified points.

Nov 26, 2019 · To cope with these issues, this paper develops a novel loss function, which adaptively emphasizes the mis-classified feature vectors to guide ...

For face recognition, current typical mining strategies are usually negligible for discriminative learning. C. Mis-classified Vector Guided Softmax Loss.

Mis-classified vector guided softmax loss for face recognition. X Wang, S Zhang, S Wang, T Fu, H Shi, T Mei. Proceedings of the AAAI Conference on Artificial ...

We develop a novel loss function, namely Hardness Loss, to adaptively assign weights for the misclassified (hard) samples guided by their corresponding ...