PATMAT: Person Aware Tuning of Mask-Aware Transformer for Face Inpainting

Generative models such as StyleGAN2 and Stable Diffusion have achieved state-of-the-art performance in computer vision tasks such as image synthesis, inpainting, and de-noising. However, current generative models for face inpainting often fail to preserve fine facial details and the identity of the person, despite creating aesthetically convincing image structures and textures. In this work, we propose Person Aware Tuning (PAT) of Mask-Aware Transformer (MAT) for face inpainting, which addresses this issue. Our proposed method, PATMAT, effectively preserves identity by incorporating reference images of a subject and fine-tuning a MAT architecture trained on faces. By using ~40 reference images, PATMAT creates anchor points in MAT's style module, and tunes the model using the fixed anchors to adapt the model to a new face identity. Moreover, PATMAT's use of multiple images per anchor during training allows the model to use fewer reference images than competing methods. We demonstrate that PATMAT outperforms state-of-the-art models in terms of image quality, the preservation of person-specific details, and the identity of the subject. Our results suggest that PATMAT can be a promising approach for improving the quality of personalized face inpainting.

Generative Visual Prompt: Unifying Distributional Control of Pre-Trained Generative Models

Generative models (e.g., GANs and diffusion models) learn the underlying data distribution in an unsupervised manner. However, many applications of interest require sampling from a specific region of the generative model's output space or evenly over a range of characteristics. To allow efficient sampling in these scenarios, we propose Generative Visual Prompt (PromptGen), a framework for distributional control over pre-trained generative models by incorporating knowledge of arbitrary off-the-shelf models. PromptGen defines control as an energy-based model (EBM) and samples images in a feed-forward manner by approximating the EBM with invertible neural networks, avoiding optimization at inference. We demonstrate how PromptGen can control several generative models (e.g., StyleGAN2, StyleNeRF, diffusion autoencoder, and NVAE) using various off-the-shelf models: (1) with the CLIP model, PromptGen can sample images guided by text, (2) with image classifiers, PromptGen can de-bias generative models across a set of attributes, and (3) with inverse graphics models, PromptGen can sample images of the same identity in different poses. (4) Finally, PromptGen reveals that the CLIP model shows "reporting bias" when used as control, and PromptGen can further de-bias this controlled distribution in an iterative manner. Our code is available at https://github.com/ChenWu98/Generative-Visual-Prompt.

Vanishing Twin GAN: How training a weak Generative Adversarial Network can improve semi-supervised image classification

Generative Adversarial Networks can learn the mapping of random noise to realistic images in a semi-supervised framework. This mapping ability can be used for semi-supervised image classification to detect images of an unknown class where there is no training data to be used for supervised classification. However, if the unknown class shares similar characteristics to the known class(es), GANs can learn to generalize and generate images that look like both classes. This generalization ability can hinder the classification performance. In this work, we propose the Vanishing Twin GAN. By training a weak GAN and using its generated output image parallel to the regular GAN, the Vanishing Twin training improves semi-supervised image classification where image similarity can hurt classification tasks.

Multi-class Generative Adversarial Nets for Semi-supervised Image Classification

From generating never-before-seen images to domain adaptation, applications of Generative Adversarial Networks (GANs) spread wide in the domain of vision and graphics problems. With the remarkable ability of GANs in learning the distribution and generating images of a particular class, they can be used for semi-supervised classification tasks. However, the problem is that if two classes of images share similar characteristics, the GAN might learn to generalize and hinder the classification of the two classes. In this paper, we use various images from MNIST and Fashion-MNIST datasets to illustrate how similar images cause the GAN to generalize, leading to the poor classification of images. We propose a modification to the traditional training of GANs that allows for improved multi-class classification in similar classes of images in a semi-supervised learning framework.

RANDGAN: Randomized Generative Adversarial Network for Detection of COVID-19 in Chest X-ray

COVID-19 spread across the globe at an immense rate has left healthcare systems incapacitated to diagnose and test patients at the needed rate. Studies have shown promising results for detection of COVID-19 from viral bacterial pneumonia in chest X-rays. Automation of COVID-19 testing using medical images can speed up the testing process of patients where health care systems lack sufficient numbers of the reverse-transcription polymerase chain reaction (RT-PCR) tests. Supervised deep learning models such as convolutional neural networks (CNN) need enough labeled data for all classes to correctly learn the task of detection. Gathering labeled data is a cumbersome task and requires time and resources which could further strain health care systems and radiologists at the early stages of a pandemic such as COVID-19. In this study, we propose a randomized generative adversarial network (RANDGAN) that detects images of an unknown class (COVID-19) from known and labelled classes (Normal and Viral Pneumonia) without the need for labels and training data from the unknown class of images (COVID-19). We used the largest publicly available COVID-19 chest X-ray dataset, COVIDx, which is comprised of Normal, Pneumonia, and COVID-19 images from multiple public databases. In this work, we use transfer learning to segment the lungs in the COVIDx dataset. Next, we show why segmentation of the region of interest (lungs) is vital to correctly learn the task of classification, specifically in datasets that contain images from different resources as it is the case for the COVIDx dataset. Finally, we show improved results in detection of COVID-19 cases using our generative model (RANDGAN) compared to conventional generative adversarial networks (GANs) for anomaly detection in medical images, improving the area under the ROC curve from 0.71 to 0.77.

Inception Augmentation Generative Adversarial Network

Successful training of convolutional neural networks (CNNs) requires a substantial amount of data. With small datasets, networks generalize poorly. Data Augmentation techniques improve the generalizability of neural networks by using existing training data more effectively. Standard data augmentation methods, however, produce limited plausible alternative data. Generative Adversarial Networks (GANs) have been utilized to generate new data and improve CNN performance. Nevertheless, generative models have not been used for augmenting data to improve the training of another generative model. In this work, we propose a new GAN architecture for semi-supervised augmentation of chest X-rays for the detection of pneumonia. We show that the proposed GAN can augment data for a specific class of images (pneumonia) using images from both classes (pneumonia and normal) in an image domain (chest X-rays). We demonstrate that using our proposed GAN-based data augmentation method significantly improves the performance of the state-of-the-art anomaly detection architecture, AnoGAN, in detecting pneumonia in chest X-rays, increasing AUC from 0.83 to 0.88.

A Transfer Learning Approach for Automated Segmentation of Prostate Whole Gland and Transition Zone in Diffusion Weighted MRI

The segmentation of prostate whole gland and transition zone in Diffusion Weighted MRI (DWI) are the first step in designing computer-aided detection algorithms for prostate cancer. However, variations in MRI acquisition parameters and scanner manufacturing result in different appearances of prostate tissue in the images. Convolutional neural networks (CNNs) which have shown to be successful in various medical image analysis tasks including segmentation are typically sensitive to the variations in imaging parameters. This sensitivity leads to poor segmentation performance of CNNs trained on a source cohort and tested on a target cohort from a different scanner and hence, it limits the applicability of CNNs for cross-cohort training and testing. Contouring prostate whole gland and transition zone in DWI images are time-consuming and expensive. Thus, it is important to enable CNNs pretrained on images of source domain, to segment images of target domain with minimum requirement for manual segmentation of images from the target domain. In this work, we propose a transfer learning method based on a modified U-net architecture and loss function, for segmentation of prostate whole gland and transition zone in DWIs using a CNN pretrained on a source dataset and tested on the target dataset. We explore the effect of the size of subset of target dataset used for fine-tuning the pre-trained CNN on the overall segmentation accuracy. Our results show that with a fine-tuning data as few as 30 patients from the target domain, the proposed transfer learning-based algorithm can reach dice score coefficient of 0.80 for both prostate whole gland and transition zone segmentation. Using a fine-tuning data of 115 patients from the target domain, dice score coefficient of 0.85 and 0.84 are achieved for segmentation of whole gland and transition zone, respectively, in the target domain.