相关论文: WildFit: Autonomous In-situ Model Adaptation for R…

The use of lightweight machine learning (ML) models in internet of things (IoT) networks enables resource constrained IoT devices to perform on-device inference for several critical applications. However, the inference accuracy deteriorates…

The Visual Domain Adaptation Challenge 2021 called for unsupervised domain adaptation methods that could improve the performance of models by transferring the knowledge obtained from source datasets to out-of-distribution target datasets.…

Self-supervised learning has emerged as a method for utilizing massive unlabeled data for pre-training models, providing an effective feature extractor for various mobile sensing applications. However, when deployed to end-users, these…

Recent transfer learning (TL) approaches in industrial intelligent fault diagnosis (FD) mostly follow the "pre-train and fine-tuning" paradigm to address data drift, which emerges from variable working conditions. However, we find that this…

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,…

In the past decade, Unmanned Aerial Vehicles (UAVs) have grabbed the attention of researchers in academia and industry for their potential use in critical emergency applications, such as providing wireless services to ground users and…

Adapting vision transformer foundation models through parameter-efficient fine-tuning (PEFT) methods has become increasingly popular. These methods optimize a limited subset of parameters, enabling efficient adaptation without the need to…

The concept of Internet of Things (IoT) has led to the development of many complex and critical systems such as smart emergency management systems. IoT-enabled applications typically depend on a communication network for transmitting large…

Next-generation IoT applications increasingly span across autonomous administrative entities, necessitating silo-cooperative scheduling to leverage diverse computational resources while preserving data privacy. However, realizing efficient…

AI systems must adapt to evolving visual environments, especially in domains where object appearances change over time. We introduce Car Models in Time (CaMiT), a fine-grained dataset capturing the temporal evolution of car models, a…

Adapting to a continuously evolving environment is a safety-critical challenge inevitably faced by all autonomous driving systems. Existing image and video driving datasets, however, fall short of capturing the mutable nature of the real…

Few-shot Test-Time Domain Adaptation focuses on adapting a model at test time to a specific domain using only a few unlabeled examples, addressing domain shift. Prior methods leverage CLIP's strong out-of-distribution (OOD) abilities by…

Detecting cyberattacks in photovoltaic (PV) monitoring and MPPT control signals requires models that are robust to bias, drift, and transient spikes, yet lightweight enough for resource-constrained edge controllers. While deep learning…

Autonomous driving requires reasoning about interactions with surrounding traffic. A prevailing approach is large-scale imitation learning on expert driving datasets, aimed at generalizing across diverse real-world scenarios. For online…

This paper proposes Shoggoth, an efficient edge-cloud collaborative architecture, for boosting inference performance on real-time video of changing scenes. Shoggoth uses online knowledge distillation to improve the accuracy of models…

Existing methods for enhancing dark images captured in a very low-light environment assume that the intensity level of the optimal output image is known and already included in the training set. However, this assumption often does not hold,…

Adapter-Tuning (AT) method involves freezing a pre-trained model and introducing trainable adapter modules to acquire downstream knowledge, thereby calibrating the model for better adaptation to downstream tasks. This paper proposes a…

We propose a new method - WildFusion - for individual identification of a broad range of animal species. The method fuses deep scores (e.g., MegaDescriptor or DINOv2) and local matching similarity (e.g., LoFTR and LightGlue) to identify…

Continual Test-time adaptation (CTTA) continuously adapts the deployed model on every incoming batch of data. While achieving optimal accuracy, existing CTTA approaches present poor real-world applicability on resource-constrained edge…

Robotic systems operating in real-world environments often suffer from concept shift, where the input-output relationship changes due to latent environmental factors that are not directly observable. Conventional adaptation methods update…