SphereFace: Deep Hypersphere Embedding for Face Recognition

Liu, Weiyang; Wen, Yandong; Yu, Zhiding; Li, Ming; Raj, Bhiksha; Song, Le

doi:10.1109/cvpr.2017.713

Cited by 2,621 publications

(2,168 citation statements)

References 25 publications

Supporting

Mentioning

2,159

Contrasting

Unclassified

Order By: Relevance

“…From the pooling layer to output, there are two fully connected layers, and it predicts speaker identity in the training set. Angular softmax [24] loss was used to train the network. The whole network structure is illustrated in Table 1.…”

Section: X-vector Modelmentioning

confidence: 99%

X-Vectors Meet Emotions: A Study On Dependencies Between Emotion and Speaker Recognition

Pappagari

Wang

Villalba

et al. 2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

In this work, we explore the dependencies between speaker recognition and emotion recognition. We first show that knowledge learned for speaker recognition can be reused for emotion recognition through transfer learning. Then, we show the effect of emotion on speaker recognition. For emotion recognition, we show that using a simple linear model is enough to obtain good performance on the features extracted from pre-trained models such as the x-vector model. Then, we improve emotion recognition performance by finetuning for emotion classification. We evaluated our experiments on three different types of datasets: IEMOCAP, MSP-Podcast, and Crema-D. By fine-tuning, we obtained 30.40%, 7.99%, and 8.61% absolute improvement on IEMOCAP, MSP-Podcast, and Crema-D respectively over baseline model with no pre-training. Finally, we present results on the effect of emotion on speaker verification. We observed that speaker verification performance is prone to changes in test speaker emotions. We found that trials with angry utterances performed worst in all three datasets. We hope our analysis will initiate a new line of research in the speaker recognition community.

show abstract

Section: X-vector Modelmentioning

confidence: 99%

X-Vectors Meet Emotions: A Study On Dependencies Between Emotion and Speaker Recognition

Pappagari

Wang

Villalba

et al. 2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

show abstract

“…Baseline (Sphereface) [16] 0.02 0.10 HCMUS notweeb [21] 0.07 0.28 DeepBlueAI [38] 0.06 0.32 ustc-nelslip [36] 0.08 0.38 vuvko [29] 0.18 0.60 P P P P Fig. 4.…”

Section: Methods Map Rank@5mentioning

confidence: 99%

Recognizing Families In the Wild (RFIW)

Robinson

Shao

Zhao

et al. 2017

Proceedings of the 2017 Workshop on Recognizing Families in the Wild

View full text Add to dashboard Cite

Recognizing Families In the Wild (RFIW)-an annual large-scale, multi-track automatic kinship recognition challenge supporting visual kin-based problems on scales larger than before. Organized in conjunction with the 15 th IEEE International Conference on Automatic Face and Gesture Recognition (FG), RFIW provides a platform for publishing original work and the gathering of experts for a discussion of the next steps. This paper summarizes the supported tasks (i.e., kinship verification, tri-subject verification, and search & retrieval of missing children) in the evaluation protocols, which include the practical motivation, technical background, data splits, metrics, and benchmark results. Furthermore, top submissions (i.e., leader-board stats) are listed and reviewed as a high-level analysis on the state of the problem. In the end, the purpose of this paper is to describe the 2020 RFIW challenge, end-to-end, along with forecasts in promising future directions.

show abstract

“…Wen et al [42] proposed the center loss to obtain the highly discriminative features for robust recognition by minimizing the interclass distance of deep features. Liu et al [23] introduced the A-softmax loss to learn angularly discriminative features for image classification on a deep hypersphere embedding manifold. Wang et al [39] embraced the idea of the Fisher criterion and proposed the large margin cosine loss (LMCL) to learn highly discriminative deep features for image recognition.…”

Section: B Loss Functions In Cnnsmentioning

confidence: 99%

The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification

Chang

Ding

Xie

et al. 2020

IEEE Trans. on Image Process.

316

102

View full text Add to dashboard Cite

Key for solving fine-grained image categorization is finding discriminate and local regions that correspond to subtle visual traits. Great strides have been made, with complex networks designed specifically to learn part-level discriminate feature representations. In this paper, we show it is possible to cultivate subtle details without the need for overly complicated network designs or training mechanisms -a single loss is all it takes. The main trick lies with how we delve into individual feature channels early on, as opposed to the convention of starting from a consolidated feature map. The proposed loss function, termed as mutual-channel loss (MC-Loss), consists of two channel-specific components: a discriminality component and a diversity component. The discriminality component forces all feature channels belonging to the same class to be discriminative, through a novel channel-wise attention mechanism. The diversity component additionally constraints channels so that they become mutually exclusive on spatial-wise. The end result is therefore a set of feature channels that each reflects different locally discriminative regions for a specific class. The MC-Loss can be trained end-to-end, without the need for any bounding-box/part annotations, and yields highly discriminative regions during inference. Experimental results show our MC-Loss when implemented on top of common base networks can achieve state-of-the-art performance on all four fine-grained categorization datasets (CUB-Birds, FGVC-Aircraft, Flowers-102, and Stanford-Cars). Ablative studies further demonstrate the superiority of MC-Loss when compared with other recently proposed general-purpose losses for visual classification, on two different base networks. Code available at https://github.com/ dongliangchang/Mutual-Channel-Loss

show abstract

SphereFace: Deep Hypersphere Embedding for Face Recognition

Cited by 2,621 publications

References 25 publications

X-Vectors Meet Emotions: A Study On Dependencies Between Emotion and Speaker Recognition

X-Vectors Meet Emotions: A Study On Dependencies Between Emotion and Speaker Recognition

Recognizing Families In the Wild (RFIW)

The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification

Contact Info

Product

Resources

About