Learning Oracle Attention for High-fidelity Face Completion

• URL: http://arxiv.org/abs/2003.13903v1
• Date: Tue, 31 Mar 2020 01:37:10 GMT
• Title: Learning Oracle Attention for High-fidelity Face Completion
• Authors: Tong Zhou, Changxing Ding, Shaowen Lin, Xinchao Wang and Dacheng Tao
• Abstract summary: 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.
• Score: 121.72704525675047
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: High-fidelity face completion is a challenging task due to the rich and subtle facial textures involved. What makes it more complicated is the correlations between different facial components, for example, the symmetry in texture and structure between both eyes. While recent works adopted the attention mechanism to learn the contextual relations among elements of the face, they have largely overlooked the disastrous impacts of inaccurate attention scores; in addition, they fail to pay sufficient attention to key facial components, the completion results of which largely determine the authenticity of a face image. Accordingly, in this paper, we design a comprehensive framework for face completion based on the U-Net structure. Specifically, we propose a dual spatial attention module to efficiently learn the correlations between facial textures at multiple scales; moreover, we provide an oracle supervision signal to the attention module to ensure that the obtained attention scores are reasonable. Furthermore, we take the location of the facial components as prior knowledge and impose a multi-discriminator on these regions, with which the fidelity of facial components is significantly promoted. Extensive experiments on two high-resolution face datasets including CelebA-HQ and Flickr-Faces-HQ demonstrate that the proposed approach outperforms state-of-the-art methods by large margins.

Related papers

• Improving Facial Landmark Detection Accuracy and Efficiency with Knowledge Distillation [4.779050216649159]
  This paper introduces a novel approach to address these challenges through the development of a knowledge distillation method. Our goal is to design models capable of accurately locating facial landmarks under varying conditions. This method was successfully implemented and achieved a top 6th place finish out of 165 participants in the IEEE ICME 2024 PAIR competition.
  arXiv  Detail & Related papers  (2024-04-09T05:30:58Z)
• LAFS: Landmark-based Facial Self-supervised Learning for Face Recognition [37.4550614524874]
  We focus on learning facial representations that can be adapted to train effective face recognition models. We explore the learning strategy of unlabeled facial images through self-supervised pretraining. Our method achieves significant improvement over the state-of-the-art on multiple face recognition benchmarks.
  arXiv  Detail & Related papers  (2024-03-13T01:07:55Z)
• DeepFidelity: Perceptual Forgery Fidelity Assessment for Deepfake Detection [67.3143177137102]
  Deepfake detection refers to detecting artificially generated or edited faces in images or videos. We propose a novel Deepfake detection framework named DeepFidelity to adaptively distinguish real and fake faces.
  arXiv  Detail & Related papers  (2023-12-07T07:19:45Z)
• 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)
• Dual Contrastive Learning for General Face Forgery Detection [64.41970626226221]
  We propose a novel face forgery detection framework, named Dual Contrastive Learning (DCL), which constructs positive and negative paired data. To explore the essential discrepancies, Intra-Instance Contrastive Learning (Intra-ICL) is introduced to focus on the local content inconsistencies prevalent in the forged faces.
  arXiv  Detail & Related papers  (2021-12-27T05:44:40Z)
• Attention-based Partial Face Recognition [6.815997591230765]
  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.
  arXiv  Detail & Related papers  (2021-06-11T14:16:06Z)
• 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)
• Dual-Attention GAN for Large-Pose Face Frontalization [59.689836951934694]
  We present a novel Dual-Attention Generative Adversarial Network (DA-GAN) for photo-realistic face frontalization. Specifically, a self-attention-based generator is introduced to integrate local features with their long-range dependencies. A novel face-attention-based discriminator is applied to emphasize local features of face regions.
  arXiv  Detail & Related papers  (2020-02-17T20:00:56Z)

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.