An official website of the United States government
Published research highlights the presence of demographic bias in automated facial attribute classification. The proposed bias mitigation techniques are mostly based on supervised learning, which requires a large amount of labeled training data for generalizability and scalability. However, labeled data is limited, requires laborious annotation, poses privacy risks, and can perpetuate human bias. In contrast, self-supervised learning (SSL) capitalizes on freely available unlabeled data, rendering trained models more scalable and generalizable. However, these label-free SSL models may also introduce biases by sampling false negative pairs, especially at low-data regimes (< 200K images) under low compute settings. Further, SSL-based models may suffer from performance degradation due to a lack of quality assurance of the unlabeled data sourced from the web. This paper proposes a fully self-supervised pipeline for demographically fair facial attribute classifiers. Leveraging completely unlabeled data pseudolabeled via pre-trained encoders, diverse data curation techniques, and meta-learning-based weighted contrastive learning, our method significantly outperforms existing SSL approaches proposed for downstream image classification tasks. Extensive evaluations on the FairFace and CelebA datasets demonstrate the efficacy of our pipeline in obtaining fair performance over existing baselines. Thus, setting a new benchmark for SSL in the fairness of facial attribute classification.
more »
« less
Toward extreme face super-resolution in the wild: A self-supervised learning approach
Extreme face super-resolution (FSR), that is, improving the resolution of face images by an extreme scaling factor (often greater than ×8) has remained underexplored in the literature of low-level vision. Extreme FSR in the wild must address the challenges of both unpaired training data and unknown degradation factors. Inspired by the latest advances in image super-resolution (SR) and self-supervised learning (SSL), we propose a novel two-step approach to FSR by introducing a mid-resolution (MR) image as the stepping stone. In the first step, we leverage ideas from SSL-based SR reconstruction of medical images (e.g., MRI and ultrasound) to modeling the realistic degradation process of face images in the real world; in the second step, we extract the latent codes from MR images and interpolate them in a self-supervised manner to facilitate artifact-suppressed image reconstruction. Our two-step extreme FSR can be interpreted as the combination of existing self-supervised CycleGAN (step 1) and StyleGAN (step 2) that overcomes the barrier of critical resolution in face recognition. Extensive experimental results have shown that our two-step approach can significantly outperform existing state-of-the-art FSR techniques, including FSRGAN, Bulat's method, and PULSE, especially for large scaling factors such as 64.
more »
« less
- Award ID(s):
- 1650474
- PAR ID:
- 10422360
- Publisher / Repository:
- Frontiers in Computer Science
- Date Published:
- Journal Name:
- Frontiers in Computer Science
- Volume:
- 4
- ISSN:
- 2624-9898
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Micro-CT, also known as X-ray micro-computed tomography, has emerged as the primary instrument for pore-scale properties study in geological materials. Several studies have used deep learning to achieve super-resolution reconstruction in order to balance the trade-off between resolution of CT images and field of view. Nevertheless, most existing methods only work with single-scale CT scans, ignoring the possibility of using multi-scale image features for image reconstruction. In this study, we proposed a super-resolution approach via multi-scale fusion using residual U-Net for rock micro-CT image reconstruction (MS-ResUnet). The residual U-Net provides an encoder-decoder structure. In each encoder layer, several residual sequential blocks and improved residual blocks are used. The decoder is composed of convolutional ReLU residual blocks and residual chained pooling blocks. During the encoding-decoding method, information transfers between neighboring multi-resolution images are fused, resulting in richer rock characteristic information. Qualitative and quantitative comparisons of sandstone, carbonate, and coal CT images demonstrate that our proposed algorithm surpasses existing approaches. Our model accurately reconstructed the intricate details of pores in carbonate and sandstone, as well as clearly visible coal cracks.more » « less
-
Self-supervised learning(SSL) is essential to obtain foundation models in NLP and CV domains via effectively leveraging knowledge in large-scale unlabeled data. The reason for its success is that a suitable SSL design can help the model to follow the neural scaling law, i.e., the performance consistently improves with increasing model and dataset sizes. However, it remains a mystery whether existing SSL in the graph domain can follow the scaling behavior toward building Graph Foundation Models~(GFMs) with large-scale pre-training. In this study, we examine whether existing graph SSL techniques can follow the neural scaling behavior with the potential to serve as the essential component for GFMs. Our benchmark includes comprehensive SSL technique implementations with analysis conducted on both the conventional SSL setting and many new settings adopted in other domains. Surprisingly, despite the SSL loss continuously decreasing, no existing graph SSL techniques follow the neural scaling behavior on the downstream performance. The model performance only merely fluctuates on different data scales and model scales. Instead of the scales, the key factors influencing the performance are the choices of model architecture and pretext task design. This paper examines existing SSL techniques for the feasibility of Graph SSL techniques in developing GFMs and opens a new direction for graph SSL design with the new evaluation prototype. Our code implementation is available online to ease reproducibility https://github.com/HaitaoMao/GraphSSLScaling.more » « less
-
Children learn powerful internal models of the world around them from a few years of egocentric visual experience. Can such internal models be learned from a child's visual experience with highly generic learning algorithms or do they require strong inductive biases? Recent advances in collecting large-scale, longitudinal, developmentally realistic video datasets and generic self-supervised learning (SSL) algorithms are allowing us to begin to tackle this nature vs. nurture question. However, existing work typically focuses on image-based SSL algorithms and visual capabilities that can be learned from static images (e.g. object recognition), thus ignoring temporal aspects of the world. To close this gap, here we train self-supervised video models on longitudinal, egocentric headcam recordings collected from a child over a two year period in their early development (6-31 months). The resulting models are highly effective at facilitating the learning of action concepts from a small number of labeled examples; they have favorable data size scaling properties; and they display emergent video interpolation capabilities. Video models also learn more robust object representations than image-based models trained with the exact same data. These results suggest that important temporal aspects of a child's internal model of the world may be learnable from their visual experience using highly generic learning algorithms and without strong inductive biases.more » « less
-
Single image 3D face reconstruction with accurate geometric details is a critical and challenging task due to the similar appearance on the face surface and fine details in organs. In this work, we introduce a self-supervised 3D face reconstruction approach from a single image that can recover detailed textures under different camera settings. The proposed network learns high-quality disparity maps from stereo face images during the training stage, while just a single face image is required to generate the 3D model in real applications. To recover fine details of each organ and facial surface, the framework introduces facial landmark spatial consistency to constrain the face recovering learning process in local point level and segmentation scheme on facial organs to constrain the correspondences at the organ level. The face shape and textures will further be refined by establishing holistic constraints based on the varying light illumination and shading information. The proposed learning framework can recover more accurate 3D facial details both quantitatively and qualitatively compared with state-of-the-art 3DMM and geometry-based reconstruction algorithms based on a single image.more » « less
