Face Images as Jigsaw Puzzles: Compositional Perception of Human Faces
for Machines Using Generative Adversarial Networks
- URL: http://arxiv.org/abs/2103.06331v1
- Date: Wed, 10 Mar 2021 20:25:38 GMT
- Title: Face Images as Jigsaw Puzzles: Compositional Perception of Human Faces
for Machines Using Generative Adversarial Networks
- Authors: Mahla Abdolahnejad and Peter Xiaoping Liu
- Abstract summary: This paper introduces a new scheme to enable generative adversarial networks to learn the distribution of face images composed of smaller parts.
We demonstrate that this model is able to produce realistic high-quality face images by generating and piecing together the parts.
- Score: 5.3683131602833525
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: An important goal in human-robot-interaction (HRI) is for machines to achieve
a close to human level of face perception. One of the important differences
between machine learning and human intelligence is the lack of
compositionality. This paper introduces a new scheme to enable generative
adversarial networks to learn the distribution of face images composed of
smaller parts. This results in a more flexible machine face perception and
easier generalization to outside training examples. We demonstrate that this
model is able to produce realistic high-quality face images by generating and
piecing together the parts. Additionally, we demonstrate that this model learns
the relations between the facial parts and their distributions. Therefore, the
specific facial parts are interchangeable between generated face images.
Related papers
- A Generalist FaceX via Learning Unified Facial Representation [77.74407008931486]
FaceX is a novel facial generalist model capable of handling diverse facial tasks simultaneously.
Our versatile FaceX achieves competitive performance compared to elaborate task-specific models on popular facial editing tasks.
arXiv Detail & Related papers (2023-12-31T17:41:48Z) - FaceChain: A Playground for Human-centric Artificial Intelligence
Generated Content [36.48960592782015]
FaceChain is a personalized portrait generation framework that combines a series of customized image-generation model and a rich set of face-related perceptual understanding models.
We inject several SOTA face models into the generation procedure, achieving a more efficient label-tagging, data-processing, and model post-processing compared to previous solutions.
Based on FaceChain, we further develop several applications to build a broader playground for better showing its value, including virtual try on and 2D talking head.
arXiv Detail & Related papers (2023-08-28T02:20:44Z) - 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) - SynFace: Face Recognition with Synthetic Data [83.15838126703719]
We devise the SynFace with identity mixup (IM) and domain mixup (DM) to mitigate the performance gap.
We also perform a systematically empirical analysis on synthetic face images to provide some insights on how to effectively utilize synthetic data for face recognition.
arXiv Detail & Related papers (2021-08-18T03:41:54Z) - Image-to-Video Generation via 3D Facial Dynamics [78.01476554323179]
We present a versatile model, FaceAnime, for various video generation tasks from still images.
Our model is versatile for various AR/VR and entertainment applications, such as face video and face video prediction.
arXiv Detail & Related papers (2021-05-31T02:30:11Z) - I Only Have Eyes for You: The Impact of Masks On Convolutional-Based
Facial Expression Recognition [78.07239208222599]
We evaluate how the recently proposed FaceChannel adapts towards recognizing facial expressions from persons with masks.
We also perform specific feature-level visualization to demonstrate how the inherent capabilities of the FaceChannel to learn and combine facial features change when in a constrained social interaction scenario.
arXiv Detail & Related papers (2021-04-16T20:03:30Z) - One-shot Face Reenactment Using Appearance Adaptive Normalization [30.615671641713945]
The paper proposes a novel generative adversarial network for one-shot face reenactment.
It can animate a single face image to a different pose-and-expression while keeping its original appearance.
arXiv Detail & Related papers (2021-02-08T03:36:30Z) - InterFaceGAN: Interpreting the Disentangled Face Representation Learned
by GANs [73.27299786083424]
We propose a framework called InterFaceGAN to interpret the disentangled face representation learned by state-of-the-art GAN models.
We first find that GANs learn various semantics in some linear subspaces of the latent space.
We then conduct a detailed study on the correlation between different semantics and manage to better disentangle them via subspace projection.
arXiv Detail & Related papers (2020-05-18T18:01:22Z) - Salient Facial Features from Humans and Deep Neural Networks [2.5211876507510724]
We explore the features that are used by humans and by convolutional neural networks (ConvNets) to classify faces.
We use Guided Backpropagation (GB) to visualize the facial features that influence the output of a ConvNet the most when identifying specific individuals.
arXiv Detail & Related papers (2020-03-08T22:41:04Z) - DotFAN: A Domain-transferred Face Augmentation Network for Pose and
Illumination Invariant Face Recognition [94.96686189033869]
We propose a 3D model-assisted domain-transferred face augmentation network (DotFAN)
DotFAN can generate a series of variants of an input face based on the knowledge distilled from existing rich face datasets collected from other domains.
Experiments show that DotFAN is beneficial for augmenting small face datasets to improve their within-class diversity.
arXiv Detail & Related papers (2020-02-23T08:16:34Z) - Domain Embedded Multi-model Generative Adversarial Networks for
Image-based Face Inpainting [44.598234654270584]
We present a domain embedded multi-model generative adversarial model for inpainting of face images with large cropped regions.
Experiments on both CelebA and CelebA-HQ face datasets demonstrate that our proposed approach achieved state-of-the-art performance.
arXiv Detail & Related papers (2020-02-05T17:36:13Z)
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.