Related papers: Adaptive and Robust Image Processing on CubeSats

Recent advancements in neural network-based optical flow estimation often come with prohibitively high computational and memory requirements, presenting challenges in their model adaptation for mobile and low-power use cases. In this paper,…

During image-guided procedures, real-time image segmentation is often required. This demands lightweight AI models that can operate on resource-constrained devices. One important use case is endoscopy-guided colonoscopy, where polyps must…

While mobile devices provide ever more compute power, improvements in DRAM bandwidth are much slower. This is unfortunate for large language model (LLM) token generation, which is heavily memory-bound. Previous work has proposed to leverage…

CubeSats are excellent platforms to rapidly perform simple space experiments. Several hundreds of CubeSats have already been successfully launched in the past few years and the number of announced launches grows every year. These platforms…

Diffusion models (DMs) have exhibited remarkable efficacy in various image restoration tasks. However, existing approaches typically operate within the high-dimensional pixel space, resulting in high computational overhead. While methods…

What if you could piece together your own custom biometrics and AI analysis system, a bit like LEGO blocks? We aim to bring that technology to field operators in the field who require flexible, high-performance edge AI system that can be…

Recent works show that convolutional neural network (CNN) architectures have a spectral bias towards lower frequencies, which has been leveraged for various image restoration tasks in the Deep Image Prior (DIP) framework. The benefit of the…

This paper presents a new exploration into a category of diffusion models built upon state space architecture. We endeavor to train diffusion models for image data, wherein the traditional U-Net backbone is supplanted by a state space…

Many recent machine learning models show dynamic shape characteristics. However, existing AI compiler optimization systems suffer a lot from problems brought by dynamic shape models, including compilation overhead, memory usage,…

Dynamic sparsity, where the sparsity patterns are unknown until runtime, poses a significant challenge to deep learning. The state-of-the-art sparsity-aware deep learning solutions are restricted to pre-defined, static sparsity patterns due…

The deep learning-based analysis of medical images suffers from data scarcity because of high annotation costs and privacy concerns. Researchers in this domain have used transfer learning to avoid overfitting when using complex…

We consider solving distributed consensus optimization problems over multi-agent networks. Current distributed methods fail to capture the heterogeneity among agents' local computation capacities. We propose DISH as a distributed hybrid…

Dataset distillation provides an effective approach to reduce memory and computational costs by optimizing a compact dataset that achieves performance comparable to the full original. However, for large-scale datasets and complex deep…

Conformal phased arrays promise shape-changing properties, multiple degrees of freedom to the scan angle, and novel applications in wearables, aerospace, defense, vehicles, and ships. However, they have suffered from two critical…

Conformal phased arrays promise shape-changing properties, multiple degrees of freedom to the scan angle, and novel applications in wearables, aerospace, defense, vehicles, and ships. However, they have suffered from two critical…

Satellites have become more widely available due to the reduction in size and cost of their components. As a result, there has been an advent of smaller organizations having the ability to deploy satellites with a variety of data-intensive…

We develop a theoretical framework for understanding dynamic morphologies and stability of droplet interface bilayers (DIBs), accounting for lipid kinetics in the monolayers and bilayer, and droplet evaporation due to imbalance between…

Video generation has been advancing rapidly, and diffusion transformer (DiT) based models have demonstrated remark- able capabilities. However, their practical deployment is of- ten hindered by slow inference speeds and high memory con-…

DIFT (Dynamic Information Flow Tracking) has been a hot topic for more than a decade. Unfortunately, existing hardware DIFT approaches have not been widely used neither by research community nor by hardware vendors. It is due to two major…

The deep learning (DL)-based methods of low-level tasks have many advantages over the traditional camera in terms of hardware prospects, error accumulation and imaging effects. Recently, the application of deep learning to replace the image…