Related papers: E2EC: An End-to-End Contour-based Method for High-…
3D object detection based on LiDAR point clouds is a crucial module in autonomous driving particularly for long range sensing. Most of the research is focused on achieving higher accuracy and these models are not optimized for deployment on…
The attributes of object contours has great significance for instance segmentation task. However, most of the current popular deep neural networks do not pay much attention to the object edge information. Inspired by the human annotation…
Most recent semi-supervised video object segmentation (VOS) methods rely on fine-tuning deep convolutional neural networks online using the given mask of the first frame or predicted masks of subsequent frames. However, the online…
Large-scale datasets with point-wise semantic and instance labels are crucial to 3D instance segmentation but also expensive. To leverage unlabeled data, previous semi-supervised 3D instance segmentation approaches have explored…
As a fundamental task in computer vision, semantic segmentation is widely applied in fields such as autonomous driving, remote sensing image analysis, and medical image processing. In recent years, Transformer-based segmentation methods…
Automated segmentation of the vertebral column in Computed Tomography (CT) scans is a prerequisite for pathological assessment and surgical planning. However, state-of-the-art methods, particularly those based on Transformers or large-scale…
Semantic segmentation is fundamental to vision systems requiring pixel-level scene understanding, yet deploying it on resource-constrained devices demands efficient architectures. Although existing methods achieve real-time inference…
Designing a driving policy for autonomous vehicles is a difficult task. Recent studies suggested an end-toend (E2E) training of a policy to predict car actuators directly from raw sensory inputs. It is appealing due to the ease of labeled…
Automated breast tumor segmentation on the basis of dynamic contrast-enhancement magnetic resonance imaging (DCE-MRI) has shown great promise in clinical practice, particularly for identifying the presence of breast disease. However,…
We introduce an efficient video segmentation system for resource-limited edge devices leveraging heterogeneous compute. Specifically, we design network models by searching across multiple dimensions of specifications for the neural…
Training high-quality instance segmentation models requires an abundance of labeled images with instance masks and classifications, which is often expensive to procure. Active learning addresses this challenge by striving for optimum…
Image segmentation is critically important in almost all medical image analysis for automatic interpretations and processing. However, it is often challenging to perform image segmentation due to data imbalance between intra- and…
Extreme Edge Computing (EEC) pushes computing even closer to end users than traditional Multi-access Edge Computing (MEC), harnessing the idle resources of Extreme Edge Devices (EEDs) to enable low-latency, distributed processing. However,…
Contour detection has been a fundamental component in many image segmentation and object detection systems. Most previous work utilizes low-level features such as texture or saliency to detect contours and then use them as cues for a…
Previous part-based attribute recognition approaches perform part detection and attribute recognition in separate steps. The parts are not optimized for attribute recognition and therefore could be sub-optimal. We present an end-to-end deep…
Current instance segmentation methods can be categorized into segmentation-based methods that segment first then do clustering, and proposal-based methods that detect first then predict masks for each instance proposal using repooling. In…
As research interests in medical image analysis become increasingly fine-grained, the cost for extensive annotation also rises. One feasible way to reduce the cost is to annotate with coarse-grained superclass labels while using limited…
Due to the high inter-class similarity caused by the complex composition and the co-existing objects across scenes, numerous studies have explored object semantic knowledge within scenes to improve scene recognition. However, a resulting…
Knowledge hypergraph embedding models are usually computationally expensive due to the inherent complex semantic information. However, existing works mainly focus on improving the effectiveness of knowledge hypergraph embedding, making the…
Recent progress in semantic segmentation is driven by deep Convolutional Neural Networks and large-scale labeled image datasets. However, data labeling for pixel-wise segmentation is tedious and costly. Moreover, a trained model can only…