Variational Potential Flow: A Novel Probabilistic Framework for Energy-Based Generative Modelling

Energy based models (EBMs) are appealing for their generality and simplicity in data likelihood modeling, but have conventionally been difficult to train due to the unstable and time-consuming implicit MCMC sampling during contrastive divergence training. In this paper, we present a novel energy-based generative framework, Variational Potential Flow (VAPO), that entirely dispenses with implicit MCMC sampling and does not rely on complementary latent models or cooperative training. The VAPO framework aims to learn a potential energy function whose gradient (flow) guides the prior samples, so that their density evolution closely follows an approximate data likelihood homotopy. An energy loss function is then formulated to minimize the Kullback-Leibler divergence between density evolution of the flow-driven prior and the data likelihood homotopy. Images can be generated after training the potential energy, by initializing the samples from Gaussian prior and solving the ODE governing the potential flow on a fixed time interval using generic ODE solvers. Experiment results show that the proposed VAPO framework is capable of generating realistic images on various image datasets. In particular, our proposed framework achieves competitive FID scores for unconditional image generation on the CIFAR-10 and CelebA datasets.

A Deep Learning Approach Using Masked Image Modeling for Reconstruction of Undersampled K-spaces

Magnetic Resonance Imaging (MRI) scans are time consuming and precarious, since the patients remain still in a confined space for extended periods of time. To reduce scanning time, some experts have experimented with undersampled k spaces, trying to use deep learning to predict the fully sampled result. These studies report that as many as 20 to 30 minutes could be saved off a scan that takes an hour or more. However, none of these studies have explored the possibility of using masked image modeling (MIM) to predict the missing parts of MRI k spaces. This study makes use of 11161 reconstructed MRI and k spaces of knee MRI images from Facebook's fastmri dataset. This tests a modified version of an existing model using baseline shifted window (Swin) and vision transformer architectures that makes use of MIM on undersampled k spaces to predict the full k space and consequently the full MRI image. Modifications were made using pytorch and numpy libraries, and were published to a github repository. After the model reconstructed the k space images, the basic Fourier transform was applied to determine the actual MRI image. Once the model reached a steady state, experimentation with hyperparameters helped to achieve pinpoint accuracy for the reconstructed images. The model was evaluated through L1 loss, gradient normalization, and structural similarity values. The model produced reconstructed images with L1 loss values averaging to <0.01 and gradient normalization values <0.1 after training finished. The reconstructed k spaces yielded structural similarity values of over 99% for both training and validation with the fully sampled k spaces, while validation loss continually decreased under 0.01. These data strongly support the idea that the algorithm works for MRI reconstruction, as they indicate the model's reconstructed image aligns extremely well with the original, fully sampled k space.

A review of deep learning methods for MRI reconstruction

Following the success of deep learning in a wide range of applications, neural network-based machine-learning techniques have received significant interest for accelerating magnetic resonance imaging (MRI) acquisition and reconstruction strategies. A number of ideas inspired by deep learning techniques for computer vision and image processing have been successfully applied to nonlinear image reconstruction in the spirit of compressed sensing for accelerated MRI. Given the rapidly growing nature of the field, it is imperative to consolidate and summarize the large number of deep learning methods that have been reported in the literature, to obtain a better understanding of the field in general. This article provides an overview of the recent developments in neural-network based approaches that have been proposed specifically for improving parallel imaging. A general background and introduction to parallel MRI is also given from a classical view of k-space based reconstruction methods. Image domain based techniques that introduce improved regularizers are covered along with k-space based methods which focus on better interpolation strategies using neural networks. While the field is rapidly evolving with thousands of papers published each year, in this review, we attempt to cover broad categories of methods that have shown good performance on publicly available data sets. Limitations and open problems are also discussed and recent efforts for producing open data sets and benchmarks for the community are examined.

Synthesize-It-Classifier: Learning a Generative Classifier through RecurrentSelf-analysis

In this work, we show the generative capability of an image classifier network by synthesizing high-resolution, photo-realistic, and diverse images at scale. The overall methodology, called Synthesize-It-Classifier (STIC), does not require an explicit generator network to estimate the density of the data distribution and sample images from that, but instead uses the classifier's knowledge of the boundary to perform gradient ascent w.r.t. class logits and then synthesizes images using Gram Matrix Metropolis Adjusted Langevin Algorithm (GRMALA) by drawing on a blank canvas. During training, the classifier iteratively uses these synthesized images as fake samples and re-estimates the class boundary in a recurrent fashion to improve both the classification accuracy and quality of synthetic images. The STIC shows the mixing of the hard fake samples (i.e. those synthesized by the one hot class conditioning), and the soft fake samples (which are synthesized as a convex combination of classes, i.e. a mixup of classes) improves class interpolation. We demonstrate an Attentive-STIC network that shows an iterative drawing of synthesized images on the ImageNet dataset that has thousands of classes. In addition, we introduce the synthesis using a class conditional score classifier (Score-STIC) instead of a normal image classifier and show improved results on several real-world datasets, i.e. ImageNet, LSUN, and CIFAR 10.

Generative Adversarial Data Programming

The paucity of large curated hand-labeled training data forms a major bottleneck in the deployment of machine learning models in computer vision and other fields. Recent work (Data Programming) has shown how distant supervision signals in the form of labeling functions can be used to obtain labels for given data in near-constant time. In this work, we present Adversarial Data Programming (ADP), which presents an adversarial methodology to generate data as well as a curated aggregated label, given a set of weak labeling functions. More interestingly, such labeling functions are often easily generalizable, thus allowing our framework to be extended to different setups, including self-supervised labeled image generation, zero-shot text to labeled image generation, transfer learning, and multi-task learning.

Zero-Shot Task Transfer

In this work, we present a novel meta-learning algorithm, i.e. TTNet, that regresses model parameters for novel tasks for which no ground truth is available (zero-shot tasks). In order to adapt to novel zero-shot tasks, our meta-learner learns from the model parameters of known tasks (with ground truth) and the correlation of known tasks to zero-shot tasks. Such intuition finds its foothold in cognitive science, where a subject (human baby) can adapt to a novel-concept (depth understanding) by correlating it with old concepts (hand movement or self-motion), without receiving explicit supervision. We evaluated our model on the Taskonomy dataset, with four tasks as zero-shot: surface-normal, room layout, depth, and camera pose estimation. These tasks were chosen based on the data acquisition complexity and the complexity associated with the learning process using a deep network. Our proposed methodology out-performs state-of-the-art models (which use ground truth)on each of our zero-shot tasks, showing promise on zero-shot task transfer. We also conducted extensive experiments to study the various choices of our methodology, as well as showed how the proposed method can also be used in transfer learning. To the best of our knowledge, this is the firstsuch effort on zero-shot learning in the task space.

C4Synth: Cross-Caption Cycle-Consistent Text-to-Image Synthesis

Generating an image from its description is a challenging task worth solving because of its numerous practical applications ranging from image editing to virtual reality. All existing methods use one single caption to generate a plausible image. A single caption by itself, can be limited, and may not be able to capture the variety of concepts and behavior that may be present in the image. We propose two deep generative models that generate an image by making use of multiple captions describing it. This is achieved by ensuring 'Cross-Caption Cycle Consistency' between the multiple captions and the generated image(s). We report quantitative and qualitative results on the standard Caltech-UCSD Birds (CUB) and Oxford-102 Flowers datasets to validate the efficacy of the proposed approach.

Adversarial Data Programming: Using GANs to Relax the Bottleneck of Curated Labeled Data

Paucity of large curated hand-labeled training data for every domain-of-interest forms a major bottleneck in the deployment of machine learning models in computer vision and other fields. Recent work (Data Programming) has shown how distant supervision signals in the form of labeling functions can be used to obtain labels for given data in near-constant time. In this work, we present Adversarial Data Programming (ADP), which presents an adversarial methodology to generate data as well as a curated aggregated label has given a set of weak labeling functions. We validated our method on the MNIST, Fashion MNIST, CIFAR 10 and SVHN datasets, and it outperformed many state-of-the-art models. We conducted extensive experiments to study its usefulness, as well as showed how the proposed ADP framework can be used for transfer learning as well as multi-task learning, where data from two domains are generated simultaneously using the framework along with the label information. Our future work will involve understanding the theoretical implications of this new framework from a game-theoretic perspective, as well as explore the performance of the method on more complex datasets.