Related papers: UFO: Unified Feature Optimization
Image fusion aims to integrate complementary information from multiple source images to produce a more informative and visually consistent representation, benefiting both human perception and downstream vision tasks. Despite recent…
This paper introduces a new path planning algorithm for unmanned aerial vehicles (UAVs) based on the teaching-learning-based optimization (TLBO) technique. We first define an objective function that incorporates requirements on the path…
Private convolutional neural network (CNN) inference based on secure two-party computation (2PC) suffers from high communication and latency overhead, especially from convolution layers. In this paper, we propose UFO, a quantized 2PC…
Multi-uncrewed aerial vehicle (UAV) cooperative perception has emerged as a promising paradigm for diverse low-altitude economy applications, where complementary multi-view observations are leveraged to enhance perception performance via…
Multiobjective optimization (MOO) is prevalent in numerous applications, in which a Pareto front (PF) is constructed to display optima under various preferences. Previous methods commonly utilize the set of Pareto objectives (particles on…
Large-scale foundation models (LFMs) have recently made impressive progress in text-to-motion generation by learning strong generative priors from massive 3D human motion datasets and paired text descriptions. However, how to effectively…
The rapid development of Unmanned aerial vehicles (UAVs) technology has spawned a wide variety of applications, such as emergency communications, regional surveillance, and disaster relief. Due to their limited battery capacity and…
Precisely detection of Unmanned Aerial Vehicles(UAVs) plays a critical role in UAV defense systems. Deep learning is widely adopted for UAV object detection whereas researches on this topic are limited by the amount of dataset and small…
We study a federated version of multi-objective optimization (MOO), where a single model is trained to optimize multiple objective functions. MOO has been extensively studied in the centralized setting but is less explored in federated or…
Vision Foundation Models (VFMs) have become the cornerstone of modern computer vision, offering robust representations across a wide array of tasks. While recent advances allow these models to handle varying input sizes during training,…
Recently, extensive research on image customization (e.g., identity, subject, style, background, etc.) demonstrates strong customization capabilities in large-scale generative models. However, most approaches are designed for specific…
This work describes the orchestration of a fleet of rotary-wing Unmanned Aerial Vehicles (UAVs) for harvesting prioritized traffic from random distributions of heterogeneous users with Multiple Input Multiple Output (MIMO) capabilities. In…
Multi-robot target tracking is a fundamental problem that requires coordinated monitoring of dynamic entities in applications such as precision agriculture, environmental monitoring, disaster response, and security surveillance. While…
Native unified multimodal models, which integrate both generative and understanding capabilities, face substantial computational overhead that hinders their real-world deployment. Existing acceleration techniques typically employ a static,…
The Unconstrained Feature Model (UFM) is a mathematical framework that enables closed-form approximations for minimal training loss and related performance measures in deep neural networks (DNNs). This paper leverages the UFM to provide…
Although advances in deep learning and aerial surveillance technology are improving wildlife conservation efforts, complex and erratic environmental conditions still pose a problem, requiring innovative solutions for cost-effective small…
By pretraining on trillions of tokens, an LLM gains the capability of text generation. However, to enhance its utility and reduce potential harm, SFT and alignment are applied sequentially to the pretrained model. Because SFT and alignment…
Tri-Planar NeRFs enable the application of powerful 2D vision models for 3D tasks, by representing 3D objects using 2D planar structures. This has made them the prevailing choice to model large collections of 3D objects. However, training…
Machine unlearning is an emerging field that selectively removes specific data samples from a trained model. This capability is crucial for addressing privacy concerns, complying with data protection regulations, and correcting errors or…
Recent vision architectures and self-supervised training methods enable vision models that are extremely accurate and general, but come with massive parameter and computational costs. In practical settings, such as camera traps, users have…