Related papers: Environment-Conditioned Diffusion Meta-Learning fo…

Diffusion models may be viewed as hierarchical variational autoencoders (VAEs) with two improvements: parameter sharing for the conditional distributions in the generative process and efficient computation of the loss as independent terms…

Multi-access edge computing (MEC) aims to extend cloud service to the network edge to reduce network traffic and service latency. A fundamental problem in MEC is how to efficiently offload heterogeneous tasks of mobile applications from…

Diffusion models have achieved promising results in image restoration tasks, yet suffer from time-consuming, excessive computational resource consumption, and unstable restoration. To address these issues, we propose a robust and efficient…

In practice, environments constantly change over time and space, posing significant challenges for object detectors trained based on a closed-set assumption, i.e., training and test data share the same distribution. To this end, continual…

Channel state information (CSI) based fingerprinting for WIFI indoor localization has attracted lots of attention very recently.The frequency diverse and temporally stable CSI better represents the location dependent channel characteristics…

Prototype-based meta-learning has emerged as a powerful technique for addressing few-shot learning challenges. However, estimating a deterministic prototype using a simple average function from a limited number of examples remains a fragile…

Relocalization is a fundamental task in the field of robotics and computer vision. There is considerable work in the field of deep camera relocalization, which directly estimates poses from raw images. However, learning-based methods have…

Deep clustering methods typically rely on a single, well-defined representation for clustering. In contrast, pretrained diffusion models provide abundant and diverse multi-scale representations across network layers and noise timesteps.…

Classical methods in robot motion planning, such as sampling-based and optimization-based methods, often struggle with scalability towards higher-dimensional state spaces and complex environments. Diffusion models, known for their…

Invariant learning methods, aimed at identifying a consistent predictor across multiple environments, are gaining prominence in out-of-distribution (OOD) generalization. Yet, when environments aren't inherent in the data, practitioners must…

For decades, fingerprint recognition has been prevalent for security, forensics, and other biometric applications. However, the availability of good-quality fingerprints is challenging, making recognition difficult. Fingerprint images might…

Diffusion and flow-based models have enabled significant progress in generation tasks across various modalities and have recently found applications in predictive learning. However, unlike typical generation tasks that encourage sample…

In the Wireless Localization Matching Problem (WLMP) the challenge is to match pieces of equipment with a set of candidate locations based on wireless signal measurements taken by the pieces of equipment. This challenge is complicated by…

Graph neural networks have shown remarkable success in exploiting the spatial and temporal patterns on dynamic graphs. However, existing GNNs exhibit poor generalization ability under distribution shifts, which is inevitable in dynamic…

Fine-grained radio map presents communication parameters of interest, e.g., received signal strength, at every point across a large geographical region. It can be leveraged to improve the efficiency of spectrum utilization for a large area,…

Accurate visual localization is crucial for autonomous driving, yet existing methods face a fundamental dilemma: While high-definition (HD) maps provide high-precision localization references, their costly construction and maintenance…

Fingerprint-based localization improves the positioning performance in challenging, non-line-of-sight (NLoS) dominated indoor environments. However, fingerprinting models require an expensive life-cycle management including recording and…

Dilated and transposed convolutions are widely used in modern convolutional neural networks (CNNs). These kernels are used extensively during CNN training and inference of applications such as image segmentation and high-resolution image…

Device-free Wi-Fi sensing has numerous benefits in practical settings, as it eliminates the requirement for dedicated sensing devices and can be accomplished using current low-cost Wi-Fi devices. With the development of Wi-Fi standards,…

Previous raw image-based low-light image enhancement methods predominantly relied on feed-forward neural networks to learn deterministic mappings from low-light to normally-exposed images. However, they failed to capture critical…