Posterior sampling in high-dimensional spaces using generative models holds significant promise for various applications, including but not limited to inverse problems and guided generation tasks. Generating diverse posterior samples remains expensive, as existing methods require restarting the entire generative process for each new sample. In this work, we propose a posterior sampling approach that simulates Langevin dynamics in the noise space of a pre-trained generative model. By exploiting the mapping between the noise and data spaces which can be provided by distilled flows or consistency models, our method enables seamless exploration of the posterior without the need to re-run the full sampling chain, drastically reducing computational overhead. Theoretically, we prove a guarantee for the proposed noise-space Langevin dynamics to approximate the posterior, assuming that the generative model sufficiently approximates the prior distribution. Our framework is experimentally validated on image restoration tasks involving noisy linear and nonlinear forward operators applied to LSUN-Bedroom (256 × 256) and ImageNet (64 × 64) datasets. The results demonstrate that our approach generates high-fidelity samples with enhanced semantic diversity even under a limited number of function evaluations, offering superior efficiency and performance compared to existing diffusion-based posterior sampling techniques.

The astonishing development of single-photon cameras has created an unprecedented opportunity for scientific and industrial imaging. However, the high data throughput generated by these 1-bit sensors creates a significant bottleneck for low-power applications. In this paper, we explore the possibility of generating a color image from a single binary frame of a single-photon camera. We evidently find this problem being particularly difficult to standard colorization approaches due to the substantial degree of exposure variation. The core innovation of our paper is an exposure synthesis model framed under a neural ordinary differential equation (Neural ODE) that allows us to generate a contin-uum of exposures from a single observation. This innovation ensures consistent exposure in binary images that col-orizers take on, resulting in notably enhanced colorization. We demonstrate applications of the method in single-image and burst colorization and show superior generative performance over baselines. Project website can be found at https://vishal-s-p.github.io/projects/2023/generative_quanta_color.html

The industrial sector has experienced a tremendous advancement in deep supervised learning due to its representation ability, but it comes with high computing and labeled data demands. Recently, the demand for intelligent IoT devices on assembly and disassembly lines has surged. This necessitates algorithms that can use data to make intelligent decisions and a framework that can enable multiple IoT devices to learn collaboratively. Further, huge image generation using IoTs also needs an efficient data annotation scheme for classification problems. WeCollab is one such framework in federated learning that significantly reduces human efforts in data annotation with breakthroughs in self-supervised learning. The proposed framework is generic and can be adapted to any specific image data generated by industrial robots involved in assembly and disassembly lines. Our method outperforms supervised learning by 25% and 20% on the CIFAR-10 and CINIC-10 datasets, respectively, for the labeling task. We generate pseudo labels for the unlabeled part of the data and train a model to achieve 30% better test accuracy on CIFAR-10 and 20% better test accuracy on the CINIC-10 dataset as compared to supervised learning. Extensive experiments unveil the effectiveness of the method and proposed combination of loss functions used by WeCollab.

Deep learning demonstrates its efficacy and potential to solve challenging computer vision problems in medical and other industrial applications. Federated learning is a learning paradigm that facilitates collaborative learning in a federation of users without exchanging actual data with a single authority like a server. However, federated learning provides only a basic level of privacy and robustness and is vulnerable to model poisoning and model inversion attacks in hostile training environments. Hence, in this article, we propose MediSecFed—a secure framework for federated learning in a hostile environment. Compared to the widely used FedAvg, our method relies on simple and practical ideas from knowledge distillation and model inversion to ensure additional security and privacy features. Our approach achieves knowledge exchange among participating entities without sharing model parameters as FedAvg does, thus protecting the privacy of the local data from the server and significantly reducing communication costs. We evaluate our method on two chest X-ray datasets. Our method outperforms FedAvg by 15% on both datasets in a hostile environment. Our method will also continue to maintain good performance even if the number of malicious participating entities increases. Robustness to learn in a malicious environment while preserving privacy with reduced communication costs makes our method more desirable and efficient than that of FedAvg.