Related papers: Progressive Self-Distillation for Ground-to-Aerial…
The existing solutions for object detection distillation rely on the availability of both a teacher model and ground-truth labels. We propose a new perspective to relax this constraint. In our framework, a student is first trained with…
With the increasing utilization of Internet of Things (IoT) enabled drones in diverse applications like photography, delivery, and surveillance, concerns regarding privacy and security have become more prominent. Drones have the ability to…
This paper presents a vision-only autonomous flight system for small UAVs operating in controlled indoor environments. The system combines semantic segmentation with monocular depth estimation to enable obstacle avoidance, scene…
Resource-constrained perception systems such as edge computing and vision-for-robotics require vision models to be both accurate and lightweight in computation and memory usage. While knowledge distillation is a proven strategy to enhance…
Cross-view localization, the task of estimating a camera's 3-degrees-of-freedom (3-DoF) pose by aligning ground-level images with satellite images, is crucial for large-scale outdoor applications like autonomous navigation and augmented…
Drones are employed in a growing number of visual recognition applications. A recent development in cell tower inspection is drone-based asset surveillance, where the autonomous flight of a drone is guided by localizing objects of interest…
Deep regression trackers are among the fastest tracking algorithms available, and therefore suitable for real-time robotic applications. However, their accuracy is inadequate in many domains due to distribution shift and overfitting. In…
Large-scale multi-view reconstruction models have made remarkable progress, but most existing approaches still rely on fully supervised training with ground-truth 3D/4D annotations. Such annotations are expensive and particularly scarce for…
Learning world models can teach an agent how the world works in an unsupervised manner. Even though it can be viewed as a special case of sequence modeling, progress for scaling world models on robotic applications such as autonomous…
Recent works have shown that optical flow can be learned by deep networks from unlabelled image pairs based on brightness constancy assumption and smoothness prior. Current approaches additionally impose an augmentation regularization term…
Autonomous drone racing has risen as a challenging robotic benchmark for testing the limits of learning, perception, planning, and control. Expert human pilots are able to fly a drone through a race track by mapping pixels from a single…
UAV Geo-Localization faces significant challenges due to the drastic appearance discrepancy between dronecaptured images and satellite views. Existing methods typically assume a consistent scaling factor across views and rely on predefined…
Pre-training a large transformer model on a massive amount of unlabeled data and fine-tuning it on labeled datasets for diverse downstream tasks has proven to be a successful strategy, for a variety of vision and natural language processing…
Autonomous navigation of drones using computer vision has achieved promising performance. Nano-sized drones based on edge computing platforms are lightweight, flexible, and cheap, thus suitable for exploring narrow spaces. However, due to…
Semi-supervised domain adaptation (SSDA) is to adapt a learner to a new domain with only a small set of labeled samples when a large labeled dataset is given on a source domain. In this paper, we propose a pair-based SSDA method that adapts…
High-quality annotation of fine-grained visual categories demands great expert knowledge, which is taxing and time consuming. Alternatively, learning fine-grained visual representation from enormous unlabeled images (e.g., species, brands)…
Depth estimation and scene segmentation are two important tasks in intelligent transportation systems. A joint modeling of these two tasks will reduce the requirement for both the storage and training efforts. This work explores how the…
Drone detection has benefited from improvements in deep neural networks, but like many other applications, suffers from the availability of accurate data for training. Synthetic data provides a potential for low-cost data generation and has…
Deep learning has raised hopes and expectations as a general solution for many applications; indeed it has proven effective, but it also showed a strong dependence on large quantities of data. Luckily, it has been shown that, even when data…
Invariance against rotations of 3D objects is an important property in analyzing 3D point set data. Conventional 3D point set DNNs having rotation invariance typically obtain accurate 3D shape features via supervised learning by using…