Related papers: JDATT: A Joint Distillation Framework for Atmosphe…
The objective of dense material segmentation is to identify the material categories for every image pixel. Recent studies adopt image patches to extract material features. Although the trained networks can improve the segmentation…
Transfer learning promises to reduce the high sample complexity of deep reinforcement learning (RL), yet existing methods struggle with domain shift between source and target environments. Policy distillation provides powerful tactical…
A variety of neural networks architectures are being studied to tackle blur in images and videos caused by a non-steady camera and objects being captured. In this paper, we present an overview of these existing networks and perform…
Adversarial attacks pose a significant threat to the security and safety of deep neural networks being applied to modern applications. More specifically, in computer vision-based tasks, experts can use the knowledge of model architecture to…
Dataset distillation creates a small distilled set that enables efficient training by capturing key information from the full dataset. While existing dataset distillation methods perform well on balanced datasets, they struggle under…
Accurate prediction of future trajectories of traffic agents is essential for ensuring safe autonomous driving. However, partially observed trajectories can significantly degrade the performance of even state-of-the-art models. Previous…
State-of-the-art text-to-image diffusion models can produce impressive visuals but may memorize and reproduce training images, creating copyright and privacy risks. Existing prompt perturbations applied at inference time, such as random…
A novel strategy is proposed to improve the accuracy of state estimation and reconstruction from low-fidelity models and sparse data from sensors. This strategy combines ensemble Data Assimilation (DA) and Machine Learning (ML) tools,…
The acquisition of high-resolution satellite imagery is often constrained by the spatial and temporal limitations of satellite sensors, as well as the high costs associated with frequent observations. These challenges hinder applications…
We design a real-time portrait matting pipeline for everyday use, particularly for "virtual backgrounds" in video conferences. Existing segmentation and matting methods prioritize accuracy and quality over throughput and efficiency, and our…
Knowledge distillation has been widely used to compress existing deep learning models while preserving the performance on a wide range of applications. In the specific context of Automatic Speech Recognition (ASR), distillation from…
Accurate multi-view 3D object detection is essential for applications such as autonomous driving. Researchers have consistently aimed to leverage LiDAR's precise spatial information to enhance camera-based detectors through methods like…
In many applications of long-range imaging, we are faced with a scenario where a person appearing in the captured imagery is often degraded by atmospheric turbulence. However, restoring such degraded images for face verification is…
Dataset distillation aims to synthesize a compact proxy dataset that is unreadable or non-raw from the original dataset for privacy protection and highly efficient learning. However, previous approaches typically adopt a single-stage…
In autonomous driving, LiDAR point-clouds and RGB images are two major data modalities with complementary cues for 3D object detection. However, it is quite difficult to sufficiently use them, due to large inter-modal discrepancies. To…
The influence of atmospheric turbulence on acquired surveillance imagery poses significant challenges in image interpretation and scene analysis. Conventional approaches for target classification and tracking are less effective under such…
Personalizing diffusion models using limited data presents significant challenges, including overfitting, loss of prior knowledge, and degradation of text alignment. Overfitting leads to shifts in the noise prediction distribution,…
Recent advances in deep learning has lead to rapid developments in the field of image retrieval. However, the best performing architectures incur significant computational cost. Recent approaches tackle this issue using knowledge…
LiDAR-based 3D object detection models have traditionally struggled under rainy conditions due to the degraded and noisy scanning signals. Previous research has attempted to address this by simulating the noise from rain to improve the…
Atmospheric turbulence degrades the performance of free-space optical (FSO) communication and remote sensing systems by introducing phase and intensity distortions. While a majority of research focuses on mitigating these effects to ensure…