paper-with-me

홈 › Papers

Pose-Robust Face Recognition via Deep Residual Equivariant Mapping

2018-03-02 · CVPR 2018 6 · Kaidi Cao, Yu Rong, Cheng Li, Xiaoou Tang, Chen Change Loy

Face recognition achieves exceptional success thanks to the emergence of deep learning. However, many contemporary face recognition models still perform relatively poor in processing profile faces compared to frontal faces. A key reason is that the number of frontal and profile training faces are highly imbalanced - there are extensively more frontal training samples compared to profile ones. In addition, it is intrinsically hard to learn a deep representation that is geometrically invariant to large pose variations. In this study, we hypothesize that there is an inherent mapping between frontal and profile faces, and consequently, their discrepancy in the deep representation space can be bridged by an equivariant mapping. To exploit this mapping, we formulate a novel Deep Residual EquivAriant Mapping (DREAM) block, which is capable of adaptively adding residuals to the input deep representation to transform a profile face representation to a canonical pose that simplifies recognition. The DREAM block consistently enhances the performance of profile face recognition for many strong deep networks, including ResNet models, without deliberately augmenting training data of profile faces. The block is easy to use, light-weight, and can be implemented with a negligible computational overhead.

📄 PDF Abstract BibTeX arXiv:1803.00839

Code (1)

penincillin/DREAM pytorch

Tasks

Face IdentificationFace RecognitionFace VerificationRobust Face Recognition

Methods 이 논문이 사용한 방법론

Average Pooling 설명 없음
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Batch Normalization 설명 없음
Bottleneck Residual Block A Bottleneck Residual Block is a variant of the residual block that utilises 1x1 convolutions to create a bottleneck. The…
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Residual Block Residual Blocks are skip-connection blocks that learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. They were introduced…
Kaiming Initialization 설명 없음

Similar Papers 제목 키워드 기반

Deep Cross-species Feature Learning for Animal Face Recognition via Residual Interspecies Equivariant Network

2020-08-01 · ECCV 2020 8 · Xiao Shi, Chenxue Yang, Xue Xia, Xiujuan Chai

Although human face recognition has achieved exceptional success driven by deep learning, animal face recognition (AFR) is still a research field that received less attention. Due to the big challenge in collecting large…

Face AlignmentFace Recognition

Co-Attentive Equivariant Neural Networks: Focusing Equivariance On Transformations Co-Occurring In Data

2019-11-18 · ICLR 2020 1 · David W. Romero, Mark Hoogendoorn

Equivariance is a nice property to have as it produces much more parameter efficient neural architectures and preserves the structure of the input through the feature mapping. Even though some combinations of transformat…

Object RecognitionRotated MNIST

Equivariant Finite Normalizing Flows

2021-10-16 · Avishek Joey Bose, Marcus Brubaker, Ivan Kobyzev

Generative modeling seeks to uncover the underlying factors that give rise to observed data that can often be modeled as the natural symmetries that manifest themselves through invariances and equivariances to certain tr…

Attention-guided Progressive Mapping for Profile Face Recognition

2021-06-27 · Junyang Huang, Changxing Ding

The past few years have witnessed great progress in the domain of face recognition thanks to advances in deep learning. However, cross pose face recognition remains a significant challenge. It is difficult for many deep …

Face Recognition

Naturally Computed Scale Invariance in the Residual Stream of ResNet18

2025-04-22 · André Longon

An important capacity in visual object recognition is invariance to image-altering variables which leave the identity of objects unchanged, such as lighting, rotation, and scale. How do neural networks achieve this? Prio…

Object Recognition