Related papers: LiRCDepth: Lightweight Radar-Camera Depth Estimati…
Recently, there have been significant improvements in the accuracy of CNN models for semantic segmentation. However, these models are often heavy and suffer from low inference speed, which limits their practical application. To address this…
Recent research on knowledge distillation has increasingly focused on logit distillation because of its simplicity, effectiveness, and versatility in model compression. In this paper, we introduce Refined Logit Distillation (RLD) to address…
Depth estimation, essential for autonomous driving, seeks to interpret the 3D environment surrounding vehicles. The development of radar sensors, known for their cost-efficiency and robustness, has spurred interest in radar-camera…
Multi-view camera-based 3D object detection has become popular due to its low cost, but accurately inferring 3D geometry solely from camera data remains challenging and may lead to inferior performance. Although distilling precise 3D…
Many radar signal processing methodologies are being developed for critical road safety perception tasks. Unfortunately, these signal processing algorithms are often poorly suited to run on embedded hardware accelerators used in…
As autonomous vehicles and advanced driving assistance systems have entered wider deployment, there is an increased interest in building robust perception systems using radars. Radar-based systems are lower cost and more robust to adverse…
The number of traffic accidents has been continuously increasing in recent years worldwide. Many accidents are caused by distracted drivers, who take their attention away from driving. Motivated by the success of Convolutional Neural…
We present a novel approach for metric dense depth estimation based on the fusion of a single-view image and a sparse, noisy Radar point cloud. The direct fusion of heterogeneous Radar and image data, or their encodings, tends to yield…
Learned image compression sits at the intersection of machine learning and image processing. With advances in deep learning, neural network-based compression methods have emerged. In this process, an encoder maps the image to a…
4D radar super-resolution, which aims to reconstruct sparse and noisy point clouds into dense and geometrically consistent representations, is a foundational problem in autonomous perception. However, existing methods often suffer from high…
Although the diffusion model has achieved remarkable performance in the field of image generation, its high inference delay hinders its wide application in edge devices with scarce computing resources. Therefore, many training-free sampling…
Developing accurate and efficient detectors for drone imagery is challenging due to the inherent complexity of aerial scenes. While some existing methods aim to achieve high accuracy by utilizing larger models, their computational cost is…
Heterogeneous distillation is an effective way to transfer knowledge from cross-architecture teacher models to student models. However, existing heterogeneous distillation methods do not take full advantage of the dark knowledge hidden in…
It remains very challenging to build a pedestrian detection system for real world applications, which demand for both accuracy and speed. This work presents a novel hierarchical knowledge distillation framework to learn a lightweight…
Monocular depth estimation (MDE) from thermal images is a crucial technology for robotic systems operating in challenging conditions such as fog, smoke, and low light. The limited availability of labeled thermal data constrains the…
Current approaches for restoration of degraded images face a trade-off: high-performance models are slow for practical use, while fast models produce poor results. Knowledge distillation transfers teacher knowledge to students, but existing…
Depth perception is crucial for a wide range of robotic applications. Multi-frame self-supervised depth estimation methods have gained research interest due to their ability to leverage large-scale, unlabeled real-world data. However, the…
Previous knowledge distillation (KD) methods mostly focus on compressing network architectures, which is not thorough enough in deployment as some costs like transmission bandwidth and imaging equipment are related to the image size.…
In the knowledge distillation literature, feature-based methods have dominated due to their ability to effectively tap into extensive teacher models. In contrast, logit-based approaches, which aim to distill "dark knowledge" from teachers,…
This paper addresses the problem of dense depth predictions from sparse distance sensor data and a single camera image on challenging weather conditions. This work explores the significance of different sensor modalities such as camera,…