Recently, learning discriminative features to improve the recognition performances gradually becomes the primary goal of deep learning, and numerous remarkable works have emerged. In this paper, we propose a novel yet extremely simple method Virtual Softmax to enhance the discriminative property of learned features by injecting a dynamic virtual negative class into the original softmax. Injecting virtual class aims to enlarge inter-class margin and compress intra-class distribution by strengthening the decision boundary constraint. Although it seems weird to optimize with this additional virtual class, we show that our method derives from an intuitive and clear motivation, and it indeed encourages the features to be more compact and separable. This paper empirically and experimentally demonstrates the superiority of Virtual Softmax, improving the performances on a variety of object classification and face verification tasks.

The paper proposes a simple technique for improved feature learning in convolutional neural networks. The technique consists of adding a "negative" virtual class to CNN training on classification tasks with the softmax loss function. The authors evaluate their approach on a range of computer vision datasets, (CIFAR10/100/100, LFW, SLLFW, CUB200, ImageNet32) and find that it outperforms simple baselines on all of them, and outperforms more complicated state-of-the-art techniques on most of them. The authors also present an analysis from a few different standpoints as to why their method is effective. Strengths: - The technique proposed by the authors is extremely simple to implement (just a one line change in existing code would suffice, as far as I can tell).

Recently, learning discriminative features to improve the recognition performances gradually becomes the primary goal of deep learning, and numerous remarkable works have emerged. In this paper, we propose a novel yet extremely simple method Virtual Softmax to enhance the discriminative property of learned features by injecting a dynamic virtual negative class into the original softmax. Injecting virtual class aims to enlarge inter-class margin and compress intra-class distribution by strengthening the decision boundary constraint. Although it seems weird to optimize with this additional virtual class, we show that our method derives from an intuitive and clear motivation, and it indeed encourages the features to be more compact and separable. This paper empirically and experimentally demonstrates the superiority of Virtual Softmax, improving the performances on a variety of object classification and face verification tasks.