Related papers: FSHNet: Fully Sparse Hybrid Network for 3D Object …
In the domain of computer vision, multi-scale feature extraction is vital for tasks such as salient object detection. However, achieving this capability in lightweight networks remains challenging due to the trade-off between efficiency and…
Salient object detection, which aims to identify and locate the most salient pixels or regions in images, has been attracting more and more interest due to its various real-world applications. However, this vision task is quite challenging,…
Few-Shot Semantic Segmentation (FSS), which focuses on segmenting new classes in images using only a limited number of annotated examples, has recently progressed in data-scarce domains. However, in this work, we show that the existing FSS…
Whole brain segmentation is an important neuroimaging task that segments the whole brain volume into anatomically labeled regions-of-interest. Convolutional neural networks have demonstrated good performance in this task. Existing…
Semantic labeling for very high resolution (VHR) images in urban areas, is of significant importance in a wide range of remote sensing applications. However, many confusing manmade objects and intricate fine-structured objects make it very…
This paper introduces HPNet, a novel deep-learning approach for segmenting a 3D shape represented as a point cloud into primitive patches. The key to deep primitive segmentation is learning a feature representation that can separate points…
Conventional deep convolutional neural networks (CNNs) apply convolution operators uniformly in space across all feature maps for hundreds of layers - this incurs a high computational cost for real-time applications. For many problems such…
Recent progress on saliency detection is substantial, benefiting mostly from the explosive development of Convolutional Neural Networks (CNNs). Semantic segmentation and saliency detection algorithms developed lately have been mostly based…
Efficient representation of point clouds is fundamental for LiDAR-based 3D object detection. While recent grid-based detectors often encode point clouds into either voxels or pillars, the distinctions between these approaches remain…
Recent non-local self-attention methods have proven to be effective in capturing long-range dependencies for semantic segmentation. These methods usually form a similarity map of RC*C (by compressing spatial dimensions) or RHW*HW (by…
Image keypoints and descriptors play a crucial role in many visual measurement tasks. In recent years, deep neural networks have been widely used to improve the performance of keypoint and descriptor extraction. However, the conventional…
We present OctNet, a representation for deep learning with sparse 3D data. In contrast to existing models, our representation enables 3D convolutional networks which are both deep and high resolution. Towards this goal, we exploit the…
Self-driving cars need to understand 3D scenes efficiently and accurately in order to drive safely. Given the limited hardware resources, existing 3D perception models are not able to recognize small instances (e.g., pedestrians, cyclists)…
Reconstructing high-fidelity fluid flow fields from sparse sensor measurements is vital for many science and engineering applications but remains challenging because of dimensional disparities between state and observational spaces. Due to…
Despite the powerful feature extraction capability of Convolutional Neural Networks, there are still some challenges in saliency detection. In this paper, we focus on two aspects of challenges: i) Since salient objects appear in various…
Object detection plays an important role in various visual applications. However, the precision and speed of detector are usually contradictory. One main reason for fast detectors' precision reduction is that small objects are hard to be…
In this paper, we focus on devising a versatile framework for dense pixelwise prediction whose goal is to assign a discrete or continuous label to each pixel for an image. It is well-known that the reduced feature resolution due to repeated…
Many LiDAR-based methods for detecting large objects, single-class object detection, or under easy situations were claimed to perform quite well. However, their performances of detecting small objects or under hard situations did not…
Cooperatively utilizing both ego-vehicle and infrastructure sensor data can significantly enhance autonomous driving perception abilities. However, the uncertain temporal asynchrony and limited communication conditions can lead to fusion…
Aggregating multi-level feature representation plays a critical role in achieving robust volumetric medical image segmentation, which is important for the auxiliary diagnosis and treatment. Unlike the recent neural architecture search (NAS)…