Face recognition has witnessed significant progress due to the advances of deep convolutional neural networks (CNNs), the central task of which is how to improve the feature discrimination. To this end, several margin-based (e.g., angular, additive and additive angular margins) softmax loss functions have been proposed to increase the feature margin between different classes. However, despite great achievements have been made, they mainly suffer from three issues: 1) Obviously, they ignore the importance of informative features mining for discriminative learning; 2) They encourage the feature margin only from the ground truth class, without realizing the discriminability from other non-ground truth classes; 3) The feature margin between different classes is set to be same and fixed, which may not adapt the situations very well. To cope with these issues, this paper develops a novel loss function, which adaptively emphasizes the mis-classified feature vectors to guide the discriminative feature learning. Thus we can address all the above issues and achieve more discriminative face features. To the best of our knowledge, this is the first attempt to inherit the advantages of feature margin and feature mining into a unified loss function. Experimental results on several benchmarks have demonstrated the effectiveness of our method over state-of-the-art alternatives. Our code is available at http://www.cbsr.ia.ac.cn/users/xiaobowang/.

Face anti-spoofing is crucial to the security of face recognition systems. Most previous methods formulate face anti-spoofing as a supervised learning problem to detect various predefined presentation attacks, which need large scale training data to cover as many attacks as possible. However, the trained model is easy to overfit several common attacks and is still vulnerable to unseen attacks. To overcome this challenge, the detector should: 1) learn discriminative features that can generalize to unseen spoofing types from predefined presentation attacks; 2) quickly adapt to new spoofing types by learning from both the predefined attacks and a few examples of the new spoofing types. Therefore, we define face anti-spoofing as a zero- and few-shot learning problem. In this paper, we propose a novel Adaptive Inner-update Meta Face Anti-Spoofing (AIM-FAS) method to tackle this problem through meta-learning. Specifically, AIM-FAS trains a meta-learner focusing on the task of detecting unseen spoofing types by learning from predefined living and spoofing faces and a few examples of new attacks. To assess the proposed approach, we propose several benchmarks for zero- and few-shot FAS. Experiments show its superior performances on the presented benchmarks to existing methods in existing zero-shot FAS protocols.

No abstract

Uneven lithium plating/stripping is an essential issue that inhibits stable cycling of a lithium metal anode and thus hinders its practical applications. The investigation of this process is challenging because it is difficult to observe lithium in an operating device. Here, we demonstrate that the microscopic lithium plating behavior can be observed in situ in a close-to-practical cell setup using X-ray computed tomography. The results reveal the formation of porous structure and its progressive evolution in space over the charging process with a large current. The elaborated analysis indicates that the microstructure of deposited lithium makes a significant impact on the subsequent lithium plating, and the impact of structural inhomogeneity, further exaggerated by the large-current charging, can lead to severely uneven lithium plating and eventually cell failure. Therefore, a codesign strategy involving delicate controls of microstructure and electrochemical conditions could be a necessity for the next-generation battery with lithium metal anode.

Optical coherence tomography (OCT) is a high-resolution and non-invasive imaging modality that has become one of the most prevalent techniques for ophthalmic diagnosis. Retinal layer segmentation is very crucial for doctors to diagnose and study retinal diseases. However, manual segmentation is often a time-consuming and subjective process. In this work, we propose a new method for automatically segmenting retinal OCT images, which integrates deep features and hand-designed features to train a structured random forests classifier. The deep convolutional features are learned from deep residual network. With the trained classifier, we can get the contour probability graph of each layer, finally the shortest path is employed to achieve the final layer segmentation. The experimental results show that our method achieves good results with the mean layer contour error of 1.215 pixels whereas that of the state-of-the-art was 1.464 pixels, and achieve a F1-score of 0.885 which is also better than 0.863 that is obtained by the state-of-the-art method.