CosFace: Large Margin Cosine Loss for Deep Face Recognition

Wang, Hao; Wang, Yitong; Zhou, Zheng; Ji, Xing; Gong, Dihong; Zhou, Jingchao; Li, Zhifeng; Liu, Wei

doi:10.1109/cvpr.2018.00552

Cited by 2,346 publications

(1,878 citation statements)

References 47 publications

Supporting

Mentioning

1,728

Contrasting

Unclassified

Order By: Relevance

“…Identity distance. We use the FaceNet (Schroff et al, 2015) to extract face features and compute the identity distance with the L 2 loss and cosine loss (Wang et al, 2018a) between the ground truth image and deblurred image. Fig.…”

Section: Face Recognitionmentioning

confidence: 99%

Exploiting Semantics for Face Image Deblurring

Shen

Lai

et al. 2020

Int J Comput Vis

View full text Add to dashboard Cite

In this paper, we propose an effective and efficient face deblurring algorithm by exploiting semantic cues via deep convolutional neural networks. As the human faces are highly structured and share unified facial components (e.g., eyes and mouths), such semantic information provides a strong prior for restoration. We incorporate face semantic labels as input priors and propose an adaptive structural loss to regularize facial local structures within an end-to-end deep convolutional neural network. Specifically, we first use a coarse deblurring network to reduce the motion blur on the input face image. We then adopt a parsing network to extract the semantic features from the coarse deblurred image. Finally, the fine deblurring network utilizes the semantic information to restore a clear face image. We train the network with perceptual and adversarial losses to generate photo-realistic results. The proposed method restores sharp images with more accurate facial features and details. Quantitative and qualitative evaluations demonstrate that the proposed face deblurring algorithm performs favorably against the state-of-the-art methods in terms of restoration quality, face recognition and execution speed.

show abstract

Section: Face Recognitionmentioning

confidence: 99%

Exploiting Semantics for Face Image Deblurring

Shen

Lai

et al. 2020

Int J Comput Vis

View full text Add to dashboard Cite

show abstract

“…Machine learning has been extensively used for failure detection [8], [28], [30], [32], attack prediction [1], [3], [4], [19], [20], [48], and face recognition [35], [37], [42]. Considering noisy labels in classification algorithms is also a problem that has been explored in the machine learning community as discussed in [5], [12], [24].…”

Section: Related Workmentioning

confidence: 99%

Robust Anomaly Detection on Unreliable Data

Zhao

Cerf

Birke

et al. 2019

2019 49th Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN)

View full text Add to dashboard Cite

Classification algorithms have been widely adopted to detect anomalies for various systems, e.g., IoT, cloud and face recognition, under the common assumption that the data source is clean, i.e., features and labels are correctly set. However, data collected from the wild can be unreliable due to careless annotations or malicious data transformation for incorrect anomaly detection. In this paper, we present a two-layer on-line learning framework for robust anomaly detection (RAD) in the presence of unreliable anomaly labels, where the first layer is to filter out the suspicious data, and the second layer detects the anomaly patterns from the remaining data. To adapt to the on-line nature of anomaly detection, we extend RAD with additional features of repetitively cleaning, conflicting opinions of classifiers, and oracle knowledge. We on-line learn from the incoming data streams and continuously cleanse the data, so as to adapt to the increasing learning capacity from the larger accumulated data set. Moreover, we explore the concept of oracle learning that provides additional information of true labels for difficult data points. We specifically focus on three use cases, (i) detecting 10 classes of IoT attacks, (ii) predicting 4 classes of task failures of big data jobs, (iii) recognising 20 celebrities faces. Our evaluation results show that RAD can robustly improve the accuracy of anomaly detection, to reach up to 98% for IoT device attacks (i.e., +11%), up to 84% for cloud task failures (i.e., +20%) under 40% noise, and up to 74% for face recognition (i.e., +28%) under 30% noisy labels. The proposed RAD is general and can be applied to different anomaly detection algorithms.

show abstract

“…Large margin cosine loss [16], Additive Margin Softmax (AM-softmax) [15] and Additive angular margin loss [2] all transform the original softmax loss function into a cosine loss style by normalizing the deep features and the weights. The normalization eliminates the variance in radial direction (compared to L-Softmax) and a cosine based margin is introduced.…”

Section: B Loss Functionmentioning

confidence: 99%

“…Recent methods [10], [9], [15], [16], [2] all expand a fixed decision margin in various manifolds. These margins constrain trained features to be compact around class center, including both hard and easy samples.…”

Section: B Adaptive Marginmentioning

confidence: 99%

See 1 more Smart Citation

Template-Instance Loss for Offline Handwritten Chinese Character Recognition

Xiao¹,

Meng²,

et al. 2019

2019 International Conference on Document Analysis and Recognition (ICDAR)

View full text Add to dashboard Cite

The long-standing challenges for offline handwritten Chinese character recognition (HCCR) are twofold: Chinese characters can be very diverse and complicated while similarly looking, and cursive handwriting (due to increased writing speed and infrequent pen lifting) makes strokes and even characters connected together in a flowing manner. In this paper, we propose the template and instance loss functions for the relevant machine learning tasks in offline handwritten Chinese character recognition. First, the character template is designed to deal with the intrinsic similarities among Chinese characters. Second, the instance loss can reduce category variance according to classification difficulty, giving a large penalty to the outlier instance of handwritten Chinese character. Trained with the new loss functions using our deep network architecture HCCR14Layer model consisting of simple layers, our extensive experiments show that it yields state-ofthe-art performance and beyond for offline HCCR.

show abstract

CosFace: Large Margin Cosine Loss for Deep Face Recognition

Cited by 2,346 publications

References 47 publications

Exploiting Semantics for Face Image Deblurring

Exploiting Semantics for Face Image Deblurring

Robust Anomaly Detection on Unreliable Data

Template-Instance Loss for Offline Handwritten Chinese Character Recognition

Contact Info

Product

Resources

About