Attention-based Partial Face Recognition
- URL: http://arxiv.org/abs/2106.06415v2
- Date: Mon, 14 Jun 2021 15:26:13 GMT
- Title: Attention-based Partial Face Recognition
- Authors: Stefan H\"ormann and Zeyuan Zhang and Martin Knoche and Torben Teepe
and Gerhard Rigoll
- Abstract summary: We propose a novel approach to partial face recognition capable of recognizing faces with different occluded areas.
We achieve this by combining attentional pooling of a ResNet's intermediate feature maps with a separate aggregation module.
Our thorough analysis demonstrates that we outperform all baselines under multiple benchmark protocols.
- Score: 6.815997591230765
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Photos of faces captured in unconstrained environments, such as large crowds,
still constitute challenges for current face recognition approaches as often
faces are occluded by objects or people in the foreground. However, few studies
have addressed the task of recognizing partial faces. In this paper, we propose
a novel approach to partial face recognition capable of recognizing faces with
different occluded areas. We achieve this by combining attentional pooling of a
ResNet's intermediate feature maps with a separate aggregation module. We
further adapt common losses to partial faces in order to ensure that the
attention maps are diverse and handle occluded parts. Our thorough analysis
demonstrates that we outperform all baselines under multiple benchmark
protocols, including naturally and synthetically occluded partial faces. This
suggests that our method successfully focuses on the relevant parts of the
occluded face.
Related papers
- COMICS: End-to-end Bi-grained Contrastive Learning for Multi-face Forgery Detection [56.7599217711363]
Face forgery recognition methods can only process one face at a time.
Most face forgery recognition methods can only process one face at a time.
We propose COMICS, an end-to-end framework for multi-face forgery detection.
arXiv Detail & Related papers (2023-08-03T03:37:13Z) - Kinship Representation Learning with Face Componential Relation [19.175823975322356]
Kinship recognition aims to determine whether the subjects in two facial images are kin or non-kin.
Most previous methods focus on designs without considering the spatial correlation between face images.
We propose the Face Componential Relation Network, which learns the relationship between face components among images with a cross-attention mechanism.
The proposed FaCoRNet outperforms previous state-of-the-art methods by large margins for the largest public kinship recognition FIW benchmark.
arXiv Detail & Related papers (2023-04-10T12:37:26Z) - Human Face Recognition from Part of a Facial Image based on Image
Stitching [0.0]
Most of the current techniques for face recognition require the presence of a full face of the person to be recognized.
In this work, we adopted the process of stitching the face by completing the missing part with the flipping of the part shown in the picture.
The selected face recognition algorithms that are applied here are Eigenfaces and geometrical methods.
arXiv Detail & Related papers (2022-03-10T19:31:57Z) - Segmentation-Reconstruction-Guided Facial Image De-occlusion [48.952656891182826]
Occlusions are very common in face images in the wild, leading to the degraded performance of face-related tasks.
This paper proposes a novel face de-occlusion model based on face segmentation and 3D face reconstruction.
arXiv Detail & Related papers (2021-12-15T10:40:08Z) - Pro-UIGAN: Progressive Face Hallucination from Occluded Thumbnails [53.080403912727604]
We propose a multi-stage Progressive Upsampling and Inpainting Generative Adversarial Network, dubbed Pro-UIGAN.
It exploits facial geometry priors to replenish and upsample (8*) the occluded and tiny faces.
Pro-UIGAN achieves visually pleasing HR faces, reaching superior performance in downstream tasks.
arXiv Detail & Related papers (2021-08-02T02:29:24Z) - The Elements of End-to-end Deep Face Recognition: A Survey of Recent
Advances [56.432660252331495]
Face recognition is one of the most popular and long-standing topics in computer vision.
Deep face recognition has made remarkable progress and been widely used in many real-world applications.
In this survey article, we present a comprehensive review about the recent advance of each element.
arXiv Detail & Related papers (2020-09-28T13:02:17Z) - Occlusion-Adaptive Deep Network for Robust Facial Expression Recognition [56.11054589916299]
We propose a landmark-guided attention branch to find and discard corrupted features from occluded regions.
An attention map is first generated to indicate if a specific facial part is occluded and guide our model to attend to non-occluded regions.
This results in more diverse and discriminative features, enabling the expression recognition system to recover even though the face is partially occluded.
arXiv Detail & Related papers (2020-05-12T20:42:55Z) - Learning Oracle Attention for High-fidelity Face Completion [121.72704525675047]
We design a comprehensive framework for face completion based on the U-Net structure.
We propose a dual spatial attention module to efficiently learn the correlations between facial textures at multiple scales.
We take the location of the facial components as prior knowledge and impose a multi-discriminator on these regions.
arXiv Detail & Related papers (2020-03-31T01:37:10Z) - SD-GAN: Structural and Denoising GAN reveals facial parts under
occlusion [7.284661356980246]
We propose a generative model to reconstruct the missing parts of the face which are under occlusion.
A novel adversarial training algorithm has been designed for a bimodal mutually exclusive Generative Adversarial Network (GAN) model.
Our proposed technique outperforms the competing methods by a considerable margin, even for boosting the performance of Face Recognition.
arXiv Detail & Related papers (2020-02-19T21:12:49Z)
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.