the Rotary Vector (RV) reducer, as one of the core components of the industrial robot execution unit, is widely used in industrial systems. Early pre-fault diagnosis and state detection are crucial and necessary for p...
详细信息
Point cloud clustering is a crucial approach to understand and analyze geometric information for both robotic systems and autonomous driving. To meet real-time requirements, several existing point cloud clustering alg...
详细信息
A printed circuit board (PCB) is a vital component of any electronic device. Over the years, the need to manufacture PCBs in large volumes has become a necessity due to technological advancement and the expansion of t...
详细信息
the electromechanical servo system is usually implemented by three closed loops, withthe inner loop being the current loop, the middle loop being the speed loop, and the outer loop being the position loop. the tradit...
详细信息
Deep Neural Networks, particularly Convolutional Neural Networks (ConvNets), have achieved incredible success in many vision tasks, but they usually require millions of parameters for good accuracy performance. With i...
详细信息
ISBN:
(数字)9781665490627
ISBN:
(纸本)9781665490627
Deep Neural Networks, particularly Convolutional Neural Networks (ConvNets), have achieved incredible success in many vision tasks, but they usually require millions of parameters for good accuracy performance. With increasing applications that use ConvNets, updating hundreds of networks for multiple tasks on an embedded device can be costly in terms of memory, bandwidth, and energy. Approaches to reduce this cost include model compression and parameter-efficient modelsthat adapt a subset of network layers for each new task. this work proposes a novel parameter-efficient kernel modulation (KM) method that adapts all parameters of a base network instead of a subset of layers. KM uses lightweight task-specialized kernel modulators that require only an additional 1.4% of the base network parameters. With multiple tasks, only the task-specialized KM weights are communicated and stored on the end-user device. We applied this method in training ConvNets for Transfer Learning and Meta-Learning scenarios. Our results show that KM delivers up to 9% higher accuracy compared to other parameter-efficient methods on the Transfer Learning benchmark.
We propose an interactive approach for 3D instance segmentation, where users can iteratively collaborate with a deep learning model to segment objects directly in a 3D point cloud. Current methods for 3D instance segm...
详细信息
ISBN:
(纸本)9798350323658
We propose an interactive approach for 3D instance segmentation, where users can iteratively collaborate with a deep learning model to segment objects directly in a 3D point cloud. Current methods for 3D instance segmentation are generally trained in a fully-supervised fashion, which requires large amounts of costly training labels, and does not generalize well to classes unseen during training. Few works have attempted to obtain 3D segmentation masks using human interactions. Existing methods rely on user feedback in the 2D image domain. As a consequence, users are required to constantly switch between 2D images and 3D representations, and custom architectures are employed to combine multiple input modalities. therefore, integration with existing standard 3D models is not straightforward. the core idea of this work is to enable users to interact directly with 3D point clouds by clicking on desired 3D objects of interest (or their background) to interactively segment the scene in an open-world setting. Specifically, our method does not require training data from any target domain and can adapt to new environments where no appropriate training sets are available. Our system continuously adjusts the object segmentation based on the user feedback and achieves accurate dense 3D segmentation masks with minimal human effort (few clicks per object). Besides its potential for efficient labeling of large-scale and varied 3D datasets, our approach, where the user directly interacts withthe 3D environment, enables new AR/VR and human-robot interaction applications.
In this paper spatially interconnected (ladder) systems have been discussed. First, the multidimensional, in that case, 2D - continuous in time and discrete in the spatial variable, has been introduced. Next, the temp...
详细信息
this paper introduces a digital current regulator with a dynamic decoupling scheme for three-phase AC motor drives that operate under low sampling to fundamental frequency ratios for high-speed motor drives. Cross-cou...
详细信息
the dynamic and accurate prediction of the target trajectory about UAVs is the key point of airspace management. For the task of air target trajectory prediction dominated by a variety of UAVs, traditional methods can...
详细信息
Powerline inspection operations involve capturing and inspecting visual footage of powerline elements from elevated positions above and around the powerline and are currently performed withthe help of helicopters and...
详细信息
ISBN:
(数字)9781665490627
ISBN:
(纸本)9781665490627
Powerline inspection operations involve capturing and inspecting visual footage of powerline elements from elevated positions above and around the powerline and are currently performed withthe help of helicopters and/or Unmanned Aerial Vehicles (UAVs). Current technological advances in the areas of robotics and machine learning are towards enabling fully autonomous operations. To this end, one of the tasks to be addressed is the robust, precise and fast powerline object detection problem. Recently introduced Transformer-based object detection methods demonstrate time and accuracy advances with respect to previous works. In this work, we present an enhanced Transformer-based architecture that further improves the state-of-the-art by incorporating a content-specific object query generator and by substituting the original attention operation with a whitening-inspired transformation at certain stages of the architecture. We evaluate our method in a recently captured powerline detection dataset and we show that our novel contributions offer a significant boost regarding detection accuracy.
暂无评论