Lunar Permanently Shadowed Regions (PSRs) are areas near the Moon’s poles that remain in perpetual darkness due to its axial tilt. Obtaining clear and high-quality images of these regions are crucial for exploring lunar surface and detecting valuable minerals. However, due to the absence of illumination, PSR images often suffer from low visibility, poor contrast, and elevated noise levels, making their enhancement a significant challenge. To overcome these challenges, this paper introduces IllumiCurveNet, a novel framework leveraging an encoder-decoder architecture with spatial attention, dilated convolutions, and adaptive gamma correction for illuminance optimization. It uses the proposed Self-Guided Loss Framework that integrates the novel texture preservation and contrast enhancement losses, along with exposure control, spatial consistency, color consistency, and total variation losses, enabling robust enhancement without paired training data. IllumiCurveNet achieves state-of-the-art performance on PSR images with no-reference image quality metrics, surpassing other zero-shot methods. The results highlight IllumiCurveNet’s potential for applications in lunar mapping, rover navigation, and resource analysis, advancing visual perception in unlit extraterrestrial environments.

After a person is arrested and charged with a crime, they may be released on bail and required to participate in a community supervision program while awaiting trial. These 'pre-trial programs' are common throughout the United States, but very little research has demonstrated their effectiveness. Researchers have emphasized the need for more rigorous program evaluation methods, which we introduce in this article. We describe a program evaluation pipeline that uses recent interpretable machine learning techniques for observational causal inference, and demonstrate these techniques in a study of a pre-trial program in Durham, North Carolina. Our findings show no evidence that the program either significantly increased or decreased the probability of new criminal charges. If these findings replicate, the criminal-legal system needs to either improve pre-trial programs or consider alternatives to them. The simplest option is to release low-risk individuals back into the community without subjecting them to any restrictions or conditions. Another option is to assign individuals to pre-trial programs that incentivize pro-social behavior. We believe that the techniques introduced here can provide researchers the rigorous tools they need to evaluate these programs.

Pretrained deep models hold their learnt knowledge in the form of model parameters. These parameters act as "memory" for the trained models and help them generalize well on unseen data. However, in absence of training data, the utility of a trained model is merely limited to either inference or better initialization towards a target task. In this paper, we go further and extract synthetic data by leveraging the learnt model parameters. We dub them Data Impressions, which act as proxy to the training data and can be used to realize a variety of tasks. These are useful in scenarios where only the pretrained models are available and the training data is not shared (e.g., due to privacy or sensitivity concerns). We show the applicability of data impressions in solving several computer vision tasks such as unsupervised domain adaptation, continual learning as well as knowledge distillation. We also study the adversarial robustness of lightweight models trained via knowledge distillation using these data impressions. Further, we demonstrate the efficacy of data impressions in generating data-free Universal Adversarial Perturbations (UAPs) with better fooling rates. Extensive experiments performed on benchmark datasets demonstrate competitive performance achieved using data impressions in absence of original training data.

GPUs are increasingly being used in real-time systems, such as autonomous vehicles, due to the vast performance benefits that they offer. As more and more applications use GPUs, more than one application may need to run on the same GPU in parallel. However, real-time systems also require predictable performance from each individual applications which GPUs do not fully support in a multi-tasking environment. Nvidia recently added a new feature in their latest GPU architecture that allows limited resource provisioning. This feature is provided in the form of a closed-source kernel module called the Multi-Process Service (MPS). However, MPS only provides the capability to partition the compute resources of GPU and does not provide any mechanism to avoid inter-application conflicts within the shared memory hierarchy. In our experiments, we find that compute resource partitioning alone is not sufficient for performance isolation. In the worst case, due to interference from co-running GPU tasks, read/write transactions can observe a slowdown of more than 10x. In this paper, we present Fractional GPUs (FGPUs), a software-only mechanism to partition both compute and memory resources of a GPU to allow parallel execution of GPU workloads with performance isolation. As many details of GPU memory hierarchy are not publicly available, we first reverse-engineer the information through various micro-benchmarks. We find that the GPU memory hierarchy is different from that of the CPU, making it well-suited for page coloring. Based on our findings, we were able to partition both the L2 cache and DRAM for multiple Nvidia GPUs. Furthermore, we show that a better strategy exists for partitioning compute resources than the one used by MPS. An FGPU combines both this strategy and memory coloring to provide superior isolation. We compare our FGPU implementation with Nvidia MPS. Compared to MPS, FGPU reduces the average variation in application runtime, in a multi-tenancy environment, from 135% to 9%. To allow multiple applications to use FGPUs seamlessly, we ported Caffe, a popular framework used for machine learning, to use our FGPU API.