Image Resolution Susceptibility of Face Recognition Models
- URL: http://arxiv.org/abs/2107.03769v1
- Date: Thu, 8 Jul 2021 11:30:27 GMT
- Title: Image Resolution Susceptibility of Face Recognition Models
- Authors: Martin Knoche, Stefan H\"ormann, Gerhard Rigoll
- Abstract summary: We first analyze the impact of image resolutions on the face verification performance with a state-of-the-art face recognition model.
For images, synthetically reduced to $5, times 5, mathrmpx$ resolution, the verification performance drops from $99.23%$ increasingly down to almost $55%$.
- Score: 8.368543987898732
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Face recognition approaches often rely on equal image resolution for
verification faces on two images. However, in practical applications, those
image resolutions are usually not in the same range due to different image
capture mechanisms or sources. In this work, we first analyze the impact of
image resolutions on the face verification performance with a state-of-the-art
face recognition model. For images, synthetically reduced to $5\, \times 5\,
\mathrm{px}$ resolution, the verification performance drops from $99.23\%$
increasingly down to almost $55\%$. Especially, for cross-resolution image
pairs (one high- and one low-resolution image), the verification accuracy
decreases even further. We investigate this behavior more in-depth by looking
at the feature distances for every 2-image test pair. To tackle this problem,
we propose the following two methods: 1) Train a state-of-the-art
face-recognition model straightforward with $50\%$ low-resolution images
directly within each batch. \\ 2) Train a siamese-network structure and adding
a cosine distance feature loss between high- and low-resolution features. Both
methods show an improvement for cross-resolution scenarios and can increase the
accuracy at very low resolution to approximately $70\%$. However, a
disadvantage is that a specific model needs to be trained for every
resolution-pair ...
Related papers
- ResFormer: Scaling ViTs with Multi-Resolution Training [100.01406895070693]
We introduce ResFormer, a framework for improved performance on a wide spectrum of, mostly unseen, testing resolutions.
In particular, ResFormer operates on replicated images of different resolutions and enforces a scale consistency loss to engage interactive information across different scales.
We demonstrate, moreover, ResFormer is flexible and can be easily extended to semantic segmentation, object detection and video action recognition.
arXiv Detail & Related papers (2022-12-01T18:57:20Z) - Octuplet Loss: Make Face Recognition Robust to Image Resolution [5.257115841810258]
We propose a novel combination of the popular triplet loss to improve robustness against image resolution.
We leverage the relationship between high-resolution images and their synthetically down-sampled variants jointly with their identity labels.
Fine-tuning several state-of-the-art approaches with our method proves that we can significantly boost performance for cross-resolution (high-to-low resolution) face verification.
arXiv Detail & Related papers (2022-07-14T08:22:58Z) - A new face swap method for image and video domains: a technical report [60.47144478048589]
We introduce a new face swap pipeline that is based on FaceShifter architecture.
New eye loss function, super-resolution block, and Gaussian-based face mask generation leads to improvements in quality.
arXiv Detail & Related papers (2022-02-07T10:15:50Z) - Resolution based Feature Distillation for Cross Resolution Person
Re-Identification [17.86505685442293]
Person re-identification (re-id) aims to retrieve images of same identities across different camera views.
Resolution mismatch occurs due to varying distances between person of interest and cameras.
We propose a Resolution based Feature Distillation (RFD) approach to overcome the problem of multiple resolutions.
arXiv Detail & Related papers (2021-09-16T11:07:59Z) - ORStereo: Occlusion-Aware Recurrent Stereo Matching for 4K-Resolution
Images [13.508624751092654]
We present the Occlusion-aware Recurrent binocular Stereo matching (ORStereo)
ORStereo generalizes to unseen high-resolution images with large disparity ranges by formulating the task as residual updates and refinements of an initial prediction.
We test the model's capability on both synthetic and real-world high-resolution images.
arXiv Detail & Related papers (2021-03-13T21:46:06Z) - Image Matching with Scale Adjustment [57.18604132027697]
We show how to represent and extract interest points at variable scales.
We devise a method allowing the comparison of two images at two different resolutions.
arXiv Detail & Related papers (2020-12-10T11:03:25Z) - Multi Scale Identity-Preserving Image-to-Image Translation Network for
Low-Resolution Face Recognition [7.6702700993064115]
We propose an identity-preserving end-to-end image-to-image translation deep neural network.
It is capable of super-resolving very low-resolution faces to their high-resolution counterparts while preserving identity-related information.
arXiv Detail & Related papers (2020-10-23T09:21:06Z) - Invertible Image Rescaling [118.2653765756915]
We develop an Invertible Rescaling Net (IRN) to produce visually-pleasing low-resolution images.
We capture the distribution of the lost information using a latent variable following a specified distribution in the downscaling process.
arXiv Detail & Related papers (2020-05-12T09:55:53Z) - Gated Fusion Network for Degraded Image Super Resolution [78.67168802945069]
We propose a dual-branch convolutional neural network to extract base features and recovered features separately.
By decomposing the feature extraction step into two task-independent streams, the dual-branch model can facilitate the training process.
arXiv Detail & Related papers (2020-03-02T13:28:32Z) - Cross-Resolution Adversarial Dual Network for Person Re-Identification
and Beyond [59.149653740463435]
Person re-identification (re-ID) aims at matching images of the same person across camera views.
Due to varying distances between cameras and persons of interest, resolution mismatch can be expected.
We propose a novel generative adversarial network to address cross-resolution person re-ID.
arXiv Detail & Related papers (2020-02-19T07:21:38Z)
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.