Related papers: Data-Driven Pixel Control: Challenges and Prospect…
In the recent years, pixel-based perceptual algorithms have been successfully applied for privacy-preserving deep learning (DL) based applications. However, their security has been broken in subsequent works by demonstrating a…
Cameras are the defacto sensor. The growing demand for real-time and low-power computer vision, coupled with trends towards high-efficiency heterogeneous systems, has given rise to a wide range of image processing acceleration techniques at…
Modern computer vision has moved beyond the domain of internet photo collections and into the physical world, guiding camera-equipped robots and autonomous cars through unstructured environments. To enable these embodied agents to interact…
When manipulating a novel object with complex dynamics, a state representation is not always available, for example for deformable objects. Learning both a representation and dynamics from observations requires large amounts of data. We…
This paper presents a simple and effective visual prompting method for adapting pre-trained models to downstream recognition tasks. Our method includes two key designs. First, rather than directly adding together the prompt and the image,…
The broad scope of obstacle avoidance has led to many kinds of computer vision-based approaches. Despite its popularity, it is not a solved problem. Traditional computer vision techniques using cameras and depth sensors often focus on…
Semantic segmentation, like other fields of computer vision, has seen a remarkable performance advance by the use of deep convolution neural networks. However, considering that neighboring pixels are heavily dependent on each other, both…
A complete dedicated electronics, from front-end to back-end, was developed to instrument a MIMAC prototype. A front end ASIC able to monitor 64 strips of pixels and to provide their individual "Time Over Threshold" information has been…
Convolutional neural networks (CNNs) are commonly used for image classification tasks, raising the challenge of their application on data flows. During their training, adaptation is often performed by tuning the learning rate. Usual…
Energy-efficient image acquisition on the edge is crucial for enabling remote sensing applications where the sensor node has weak compute capabilities and must transmit data to a remote server/cloud for processing. To reduce the edge energy…
Lossy image coding standards such as JPEG and MPEG have successfully achieved high compression rates for human consumption of multimedia data. However, with the increasing prevalence of IoT devices, drones, and self-driving cars, machines…
Growing diversity and complexity of on-chip photonic applications requires rapid design of components with state-of-the-art operation metrics. Here, we demonstrate a highly flexible and efficient method for designing several classes of…
One approach for feedback control using high dimensional and rich sensor measurements is to classify the measurement into one out of a finite set of situations, each situation corresponding to a (known) control action. This approach…
Visual intelligence at the edge is becoming a growing necessity for low latency applications and situations where real-time decision is vital. Object detection, the first step in visual data analytics, has enjoyed significant improvements…
Recent advances in unsupervised representation learning significantly improved the sample efficiency of training Reinforcement Learning policies in simulated environments. However, similar gains have not yet been seen for real-robot…
This chapter covers the development of feedback control of superconducting qubits using projective measurement and a discrete set of conditional actions, here referred to as digital feedback. We begin with an overview of the applications of…
We propose a robust data-driven output feedback control algorithm that explicitly incorporates inherent finite-sample model estimate uncertainties into the control design. The algorithm has three components: (1) a subspace identification…
Recent work has shown that learned image compression strategies can outperform standard hand-crafted compression algorithms that have been developed over decades of intensive research on the rate-distortion trade-off. With growing…
The widespread adoption of machine learning and other matrix intensive computing algorithms has inspired renewed interest in analog optical computing, which has the potential to perform large-scale matrix multiplications with superior…
Current video-based computer vision (CV) applications typically suffer from high energy consumption due to reading and processing all pixels in a frame, regardless of their significance. While previous works have attempted to reduce this…