Towards Universal Representation Learning for Deep Face Recognition
- URL: http://arxiv.org/abs/2002.11841v1
- Date: Wed, 26 Feb 2020 23:29:57 GMT
- Title: Towards Universal Representation Learning for Deep Face Recognition
- Authors: Yichun Shi, Xiang Yu, Kihyuk Sohn, Manmohan Chandraker, and Anil K.
Jain
- Abstract summary: We propose a universal representation learning framework that can deal with larger variation unseen in the given training data without leveraging target domain knowledge.
Experiments show that our method achieves top performance on general face recognition datasets such as LFW and MegaFace.
- Score: 106.21744671876704
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Recognizing wild faces is extremely hard as they appear with all kinds of
variations. Traditional methods either train with specifically annotated
variation data from target domains, or by introducing unlabeled target
variation data to adapt from the training data. Instead, we propose a universal
representation learning framework that can deal with larger variation unseen in
the given training data without leveraging target domain knowledge. We firstly
synthesize training data alongside some semantically meaningful variations,
such as low resolution, occlusion and head pose. However, directly feeding the
augmented data for training will not converge well as the newly introduced
samples are mostly hard examples. We propose to split the feature embedding
into multiple sub-embeddings, and associate different confidence values for
each sub-embedding to smooth the training procedure. The sub-embeddings are
further decorrelated by regularizing variation classification loss and
variation adversarial loss on different partitions of them. Experiments show
that our method achieves top performance on general face recognition datasets
such as LFW and MegaFace, while significantly better on extreme benchmarks such
as TinyFace and IJB-S.
Related papers
- Boosting Unconstrained Face Recognition with Targeted Style Adversary [10.428185253933004]
We present a simple yet effective method to expand the training data by interpolating between instance-level feature statistics across labeled and unlabeled sets.
Our method, dubbed Targeted Style Adversary (TSA), is motivated by two observations: (i) the input domain is reflected in feature statistics, and (ii) face recognition model performance is influenced by style information.
arXiv Detail & Related papers (2024-08-14T16:13:03Z) - Exploring Data Augmentations on Self-/Semi-/Fully- Supervised
Pre-trained Models [24.376036129920948]
We investigate how data augmentation affects performance of vision pre-trained models.
We apply 4 types of data augmentations termed with Random Erasing, CutOut, CutMix and MixUp.
We report their performance on vision tasks such as image classification, object detection, instance segmentation, and semantic segmentation.
arXiv Detail & Related papers (2023-10-28T23:46:31Z) - Fine-grained Recognition with Learnable Semantic Data Augmentation [68.48892326854494]
Fine-grained image recognition is a longstanding computer vision challenge.
We propose diversifying the training data at the feature-level to alleviate the discriminative region loss problem.
Our method significantly improves the generalization performance on several popular classification networks.
arXiv Detail & Related papers (2023-09-01T11:15:50Z) - A Novel Cross-Perturbation for Single Domain Generalization [54.612933105967606]
Single domain generalization aims to enhance the ability of the model to generalize to unknown domains when trained on a single source domain.
The limited diversity in the training data hampers the learning of domain-invariant features, resulting in compromised generalization performance.
We propose CPerb, a simple yet effective cross-perturbation method to enhance the diversity of the training data.
arXiv Detail & Related papers (2023-08-02T03:16:12Z) - Improving Deep Metric Learning by Divide and Conquer [11.380358587116683]
Deep metric learning (DML) is a cornerstone of many computer vision applications.
It aims at learning a mapping from the input domain to an embedding space, where semantically similar objects are located nearby and dissimilar objects far from another.
We propose to build a more expressive representation by splitting the embedding space and the data hierarchically into smaller sub-parts.
arXiv Detail & Related papers (2021-09-09T02:57:34Z) - Cross-Domain Similarity Learning for Face Recognition in Unseen Domains [90.35908506994365]
We introduce a novel cross-domain metric learning loss, which we dub Cross-Domain Triplet (CDT) loss, to improve face recognition in unseen domains.
The CDT loss encourages learning semantically meaningful features by enforcing compact feature clusters of identities from one domain.
Our method does not require careful hard-pair sample mining and filtering strategy during training.
arXiv Detail & Related papers (2021-03-12T19:48:01Z) - Guided Interpolation for Adversarial Training [73.91493448651306]
As training progresses, the training data becomes less and less attackable, undermining the robustness enhancement.
We propose the guided framework (GIF), which employs the previous epoch's meta information to guide the data's adversarial variants.
Compared with the vanilla mixup, the GIF can provide a higher ratio of attackable data, which is beneficial to the robustness enhancement.
arXiv Detail & Related papers (2021-02-15T03:55:08Z) - SSDL: Self-Supervised Domain Learning for Improved Face Recognition [0.0]
Face recognition in unconstrained environments is challenging due to variations in illumination, quality of sensing, motion blur and etc.
We propose a self-supervised domain learning scheme that trains on triplets mined from unlabelled data.
arXiv Detail & Related papers (2020-11-26T15:55:59Z) - Omni-supervised Facial Expression Recognition via Distilled Data [120.11782405714234]
We propose omni-supervised learning to exploit reliable samples in a large amount of unlabeled data for network training.
We experimentally verify that the new dataset can significantly improve the ability of the learned FER model.
To tackle this, we propose to apply a dataset distillation strategy to compress the created dataset into several informative class-wise images.
arXiv Detail & Related papers (2020-05-18T09:36:51Z) - Sharing Matters for Generalization in Deep Metric Learning [22.243744691711452]
This work investigates how to learn characteristics that separate between classes without the need for annotations or training data.
By formulating our approach as a novel triplet sampling strategy, it can be easily applied on top of recent ranking loss frameworks.
arXiv Detail & Related papers (2020-04-12T10:21:15Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.