DiFace: Cross-Modal Face Recognition through Controlled Diffusion

• URL: http://arxiv.org/abs/2312.01367v1
• Date: Sun, 3 Dec 2023 12:28:52 GMT
• Title: DiFace: Cross-Modal Face Recognition through Controlled Diffusion
• Authors: Bowen Sun, Shibao Zheng
• Abstract summary: Diffusion probabilistic models (DPMs) have exhibited exceptional proficiency in generating visual media of outstanding quality and realism. We present DiFace, a solution that effectively achieves face recognition via text through a controllable diffusion process. Our approach achieves, to the best of our knowledge, a significant accuracy in text-to-image face recognition for the first time.
• Score: 3.8496256387884378
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Diffusion probabilistic models (DPMs) have exhibited exceptional proficiency in generating visual media of outstanding quality and realism. Nonetheless, their potential in non-generative domains, such as face recognition, has yet to be thoroughly investigated. Meanwhile, despite the extensive development of multi-modal face recognition methods, their emphasis has predominantly centered on visual modalities. In this context, face recognition through textual description presents a unique and promising solution that not only transcends the limitations from application scenarios but also expands the potential for research in the field of cross-modal face recognition. It is regrettable that this avenue remains unexplored and underutilized, a consequence from the challenges mainly associated with three aspects: 1) the intrinsic imprecision of verbal descriptions; 2) the significant gaps between texts and images; and 3) the immense hurdle posed by insufficient databases.To tackle this problem, we present DiFace, a solution that effectively achieves face recognition via text through a controllable diffusion process, by establishing its theoretical connection with probability transport. Our approach not only unleashes the potential of DPMs across a broader spectrum of tasks but also achieves, to the best of our knowledge, a significant accuracy in text-to-image face recognition for the first time, as demonstrated by our experiments on verification and identification.

Related papers

• Object recognition in primates: What can early visual areas contribute? [0.0]
  We investigate how signals carried by early visual processing areas could be used for object recognition in the periphery. Models of V1 simple or complex cells could provide quite reliable information, resulting in performance better than 80% in realistic scenarios. We propose that object recognition should be seen as a parallel process, with high-accuracy foveal modules operating in parallel with lower-accuracy and faster modules that can operate across the visual field.
  arXiv  Detail & Related papers  (2024-07-05T18:57:09Z)
• Effective Adapter for Face Recognition in the Wild [72.75516495170199]
  We tackle the challenge of face recognition in the wild, where images often suffer from low quality and real-world distortions. Traditional approaches-either training models directly on degraded images or their enhanced counterparts using face restoration techniques-have proven ineffective. We propose an effective adapter for augmenting existing face recognition models trained on high-quality facial datasets.
  arXiv  Detail & Related papers  (2023-12-04T08:55:46Z)
• Harnessing Unrecognizable Faces for Face Recognition [87.80037162457427]
  We propose a measure of recognizability of a face image, implemented by a deep neural network trained using mostly recognizable identities. We show that accounting for recognizability reduces error rate of single-image face recognition by 58% at FAR=1e-5.
  arXiv  Detail & Related papers  (2021-06-08T05:25:03Z)
• How Unique Is a Face: An Investigative Study [8.803279436922267]
  We study the impact of factors such as image resolution, feature representation, database size, age and gender on uniqueness denoted by the Kullback-Leibler divergence between genuine and impostor distributions. We present experimental results on the datasets AT&T, LFW, IMDb-Face, as well as ND-TWINS, with the feature extraction algorithms VGGFace, VGG16, ResNet50, InceptionV3, MobileNet and DenseNet121.
  arXiv  Detail & Related papers  (2021-02-09T17:35:39Z)
• Facial Expressions as a Vulnerability in Face Recognition [73.85525896663371]
  This work explores facial expression bias as a security vulnerability of face recognition systems. We present a comprehensive analysis of how facial expression bias impacts the performance of face recognition technologies.
  arXiv  Detail & Related papers  (2020-11-17T18:12:41Z)
• A survey of face recognition techniques under occlusion [4.10247419557141]
  occluded face recognition is imperative to exploit the full potential of face recognition for real-world applications. We present how existing face recognition methods cope with the occlusion problem and classify them into three categories. We analyze the motivations, innovations, pros and cons, and the performance of representative approaches for comparison.
  arXiv  Detail & Related papers  (2020-06-19T20:44:02Z)
• 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)
• Investigating the Impact of Inclusion in Face Recognition Training Data on Individual Face Identification [93.5538147928669]
  We audit ArcFace, a state-of-the-art, open source face recognition system, in a large-scale face identification experiment with more than one million distractor images. We find a Rank-1 face identification accuracy of 79.71% for individuals present in the model's training data and an accuracy of 75.73% for those not present.
  arXiv  Detail & Related papers  (2020-01-09T15:50:28Z)

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.